On a completely different topic, I wanted to share some videos which many readers of this blog will enjoy. These are the videos of the 2015 Breakthrough Prize in Mathematics Symposium, with speakers (and prize winners) Jacob Lurie, Terence Tao, Maxim Kontsevich, Richard Taylor, and Simon Donaldson. They were asked to give talks to a general audience, and they succeeded at different levels. Both Taylor and Lurie took this request very seriously, perhaps a bit too much even, and their talks (here and here) are very elementary (yet still entertaining!). Tao talks about the Polymath projects, and the video can be safely skipped unless you have never heard of Polymath. I understood nothing of Kontsevich’s talk (it’s pretty funny to think that his talk was prepared with the guideline of aiming at a general audience). My favorite talk by far was the one by Donaldson. Thanks to him I finally understand what the extra 7 unobserved dimensions of our universe could look like! There is also a panel discussion led by Yuri Milner with the 5 mathematicians. Unfortunately the questions are a bit dull, so there is not much that the panelists can do to make this interesting. Yet there are a few gems in the answers, such as Tao claiming that *universality* (such as in the Central Limit Theorem) is behind the unreasonable effectiveness of mathematics in physics, and Kontsevich who replies to Tao that this is a valid point at the macroscopic level, but the fact that mathematics work so well at a microscopic level (e.g., quantum mechanics) makes him question whether we live in a simulation. Kontsevich also says that there is no fundamental obstacle to building an A.I., and he even claims that he gave some thoughts to this problem, though I could not find any paper written by him on this matter.

**COLT 2015 accepted papers**

On Consistent Surrogate Risk Minimization and Property Elicitation

Minimax Fixed-Design Linear Regression

Sequential Information Maximization: When is Greedy Near-optimal?

– Learnability of Solutions to Conjunctive Queries: The Full Dichotomy

Efficient Sampling for Gaussian Graphical Models via Spectral Sparsification

On-Line Learning Algorithms for Path Experts with Non-Additive Losses

Truthful Linear Regression

$S^2$: An Efficient Graph Based Active Learning Algorithm with Application to Nonparametric Classification

Convex Risk Minimization and Conditional Probability Estimation

Beyond Hartigan Consistency: Merge Distortion Metric for Hierarchical Clustering

– Learning and inference in the presence of corrupted inputs

Vector-Valued Property Elicitation

Learning the dependence structure of rare events: a non-asymptotic study

Adaptive recovery of signals by convex optimization

Tensor principal component analysis

Learning Overcomplete Latent Variable Models through Tensor Methods

Exp-Concavity of Proper Composite Losses

On Learning Distributions from their Samples

– Online PCA with Spectral Bounds

– Regret Lower Bound and Optimal Algorithm in Dueling Bandit Problem

Hierarchical label queries with data-dependent partitions

– Bad Universal Priors and Notions of Optimality

Lower and Upper Bounds on the Generalization of Stochastic Exponentially Concave Optimization

Correlation Clustering with Noisy Partial Information

– Online Density Estimation of Bradley-Terry Models

Cortical Learning via Prediction

– Partitioning Well-Clustered Graphs: Spectral Clustering Works!

Batched Bandit Problems

– Fast Mixing for Discrete Point Processes

– An Almost Optimal PAC Algorithm

Minimax rates for memory-bounded sparse linear regression

Regularized Linear Regression: A Precise Analysis of the Estimation Error

Max vs Min: Tensor Decomposition and ICA with nearly Linear Sample Complexity

On Convergence of Emphatic Temporal-Difference Learning

]]>So what is deep learning? Well, from my current limited understanding, it seems to be a pretty simple supervised learning technique which can be explained in a few lines. Of course, simple problems can be very deep (ever heard of the Collatz conjecture?), and it looks like this may be the case with deep learning. After explaining what is deep learning (or more accurately what is my understanding of deep learning), I will point out some recent theoretical progress towards understanding the basic phenomenona at play. Let me be clear right away: it seems to me that no one has a real clue about what’s going on.

**Deep learning: it’s all about the features**

Ok, so, you have a data set with and . Typically is an image, and is say if there is a pinguin in this image. A very efficient algorithm to learn a mapping from to is to use some kind of linear classification, such as multi-class logistic regression (see also this post for some background on linear classification). However applying a linear classification directly on typically does not work very well, and this why we usually first map the point to , where is some feature map. Designing has been part of the art of machine learning, and the idea behind deep learning is to incorporate the problem of finding a good map as part of the learning process (again in the previous post on linear classification I also discussed this possibility in the context of SVM, though we ended up with a semi-definite program which does not scale well with large data sets).

Ok so what kind of do we look at in deep learning? Well they are of the following form, for some sequence of matrices , with :

The (non-linear) mappings are fixed and part of the design choice (i.e., they are not learned). The parameters are also specified beforehand. Furthermore one usually impose extra constraints on the matrices , such as having all columns bounded in -norm (say by ).

The game now is simply to incorporate the matrices as free variables when one performs the optimization of the multiclass logistic loss. This optimization is always performed with Stochastic Gradient Descent (or a simple variant of it, such as mini-batch SGD, see this post and Section 6.2 in my survey): take an example in your data set ; compute the gradient of the logistic loss at this example (with respect to the matrices and the logistic regression weights), and do a small step in the opposite direction of the gradient.

**Design choices**

Part of the success of deep learning is in the choices left open above, such as the choice of the non-linear maps, and the set of constraints on the matrices. Let me partly describe some of these choices that Krizhevsky, Sutskever and Hinton used for their computer vision breakthrough where they basically halfed the error rate of the competition on the ImageNet dataset (the details can be found here).

First they take . Then and are the so-called ReLU function (Rectified Linear Unit), which simply take the positive part coordinate-wise. On the other hand are composition of ReLU with *max-pooling*. The max-pooling is a dimension reduction operation, which simply takes adjacent coordinates (in the case of an image, adjacent pixels) and returns the maximal element. Regarding the constraints on the matrices, and are left unconstrained (besides perhaps the energy control on the columns), while are highly structure *convolutional networks*, or ConvNets as they are usually called. Essentially this means that in these matrices, the columns up to are translations of some very sparse vector. Precisely, for , they take and each sparse vector corresponds to a image. In other words the vector corresponds to a collection of images, each one of them being the convolution of with a small patch (whose weights are being learned).

While this post is not about the history of deep learning (this has been discussed at length pretty much everywhere on the internet), I still would like to point out that the apparently arbitrary choice behind max-pooling and the ConvNets are due to Yann LeCun, who has experimented with these for many many years.

**Some mysterious steps**

So far I would say that the method described above kind of make sense (apart from the max-pooling operation which I really do not understand). But things are now going to turn out a bit more wacky than you might have expected. First note that there is one key element missing from my description of the learning algorithm: what does “small” mean in the sentence “take a small step in the opposite direction of the gradient”. If you know about convex optimization and machine learning, then you know that a lot of work usually goes into understanding precisely what kind of learning rate one should take, and in particular at which rate one should decrease it over time. In deep learning all of this theory goes out of the window since the objective function is not convex (note that there is *some *convexity in the sense that the objective is convex in – thanks to Nicolas Le Roux for fixing a mistake in the first version of the previous sentence). Here it seems that the current state of the art is to start with some guess, say , then look at how the training error decays as more examples are being processed, and if the training error plateau then just divide the learning rate by .

Another point which seems key to the success of such an architecture is to control overfitting. Again for a convex problem we know that one-pass through the data with SGD and the appropriate learning rate would work just fine in terms of generalization error. In deep learning the algorithm makes multiple passes on the data, and furthermore the problem is non-convex. This strongly suggests that overfitting will be a real problem, especially given the number of free parameters. Thankfully Hinton and his colleagues invented a quite smart technique, called “dropout”. The idea is simply to take the gradient with respect to only half of the columns of the matrices , where the half is chosen at random at each iteration. In the network view of the architecture this amounts to “dropping” each unit with probability . Intuitively this forces the network to be more robust, and to “repeat” itself, thus avoiding overfitting.

**Hacking through life**

Of course, if you want to beat everyone else in the world at something, you better have every parts of your system completely optimized. In that respect the deep learning community took the implementation of the above ideas to the next level by using GPUs, thus making the computation of the gradients much faster (by the way, the ReLU non-linearity also helps here, compared to more traditional non-linearities such as sigmoids). Various other tricks are being used, such as artificially expanding the data set by altering the (e.g., by translating the images) or by running the network backward.

**Towards an understanding of deep learning?**

I think it’s fair to say that we do not understand why deep nets work at all, and we understand even less why they are doing so much better than anything else. The three main questions are: (i) why is SGD meaningful for this non-convex problem, (ii) why is dropout enough to avoid overfitting, (iii) can we explain why ConvNets are a sensible way to learn representations?

Very limited progress has been made on these questions, though I will cite some papers that at least try to attack these problems. I try to summarize each work with one sentence, see the papers for more details (and in particular the details will reveal that these papers do not make direct progress on the above questions).

– Sanjeev Arora and his co-authors proved that a “random and sparse” deep net can be learned in polynomial time.

– Roi Livni, Shai Shalev-Shwartz and Ohad Shamir obtain some results on the approximation power of a neural network with a non-linearity of the form .

– Gerard Ben Arous, Yann LeCun and their students draw an interesting connection between fully connected neural networks (such as the last 3 layers in the above architecture) and spherical spin glasses.

– Stephane Mallat gives some insights on (iii) via the scattering transform. Arnab Paul and Suresh Venkat borrow ideas from group theory to shed some light on (iii).

– Francis Bach proves some generalization bounds for neural networks with one hidden layer.

I apologize for misrepresenting deep learning so badly in this post. I know I missed a lot, and you’re welcome to correct me in the comments!

**Edit. Some further references added thanks to various comments:**

– Approaches for (ii): David McAllester with PAC-Bayesian bounds, and Percy Liang and students with a link to AdaGrad.

– Approach to (iii) by a group at Facebook on the relevance of ConvNets for certain natural distributions.

– I said in the post that all optimization theory goes out of the window when the problem is non-convex. This is of course not true, and for instance a 1998 paper by Leon Bottou has results for SGD in more general scenario. However in the non-convex case we only have very weak guarantees which basically say nothing about the global optimum.

]]>In this blog post I want to discuss some of the most famous (or infamous in some cases) spatial models of network growth. For simplicity, and also to draw pictures, everything will be described in the plane, and specifically on the lattice . These models iteratively build an aggregate as follows: First . Then where is a random point in the boundary of the aggregate, that is . Thus a model is defined by the probability measure one puts on the boundary of the aggregate to select the next point to add.

All the pictures are with half a million particles, and the particles are colored as a function of their age, with blue corresponding to old particles, and red corresponding to young ones.

**Eden model**

The simplest model uses the uniform measure on the boundary, and it is known as the *Eden model*. Here is a picture:

One of the most basic result about this model is that it admits a limit shape:

Theorem:There exists a (deterministic) convex set such that for any ,

It is known that is not an Euclidean ball (this should be clear from the picture), though nobody knows what is exactly. How do you prove such a theorem? Well it turns out to be pretty easy once you have the right machinery. The first step is to realize that the Eden model exactly corresponds to first passage percolation with exponential clocks: imagine that you have i.i.d. exponential random variables on the edges of , and consider to be the set of points such that there exists a path from to with . In other words is the set of points reached at time by a fluid released at time in and with travel times on the edges given by the random variables . It is an easy exercise to convince yourself that has the same distribution as conditionally on (this is actually not true, one in fact needs to put the travel times on the *vertices* of rather than on the edges, but let me get away with that small mistake). At this point the continuous version of the above theorem can be rather easily proved via Kingman’s subadditive ergodic theorem, see the Saint Flour lecture notes by Kesten for more details.

**Diffusion Limited Aggregation (DLA)**

Here we consider the harmonic measure from infinity: pick a point of uniformly at random from a large circle that contains , and then start a random walk from this point until it hits (which will happen eventually since a simple random walk in two dimensions is recurrent); let be the latter point. Here is a global picture and a zoom (the same pictures in black and white are provided at the end of this section):

Absolutely nothing is known about this model apart from the following simple result of Kesten:

A fascinating open problem is to show that for some ,

which the above picture clearly seems to validate. Note that at the moment nobody can even prove that once rescaled by the DLA will not converge to an Euclidean ball…

**Ballistic DLA**

Here is a model that, as far as I know, was introduced by Ronen Eldan. Instead of having one particle coming from infinity to hit the aggregate through a random walk, imagine now that the aggregate is constantly bombarded (ballistically). Precisely particles are coming from infinity in every direction (that is on every line) at a constant rate. In other words first select a direction uniformly at random, and then among the lines parallel to that direction that hit the current aggregate choose one uniformly at random. The added point is the boundary point at the intersection of this (oriented) line with the aggregate. Here is a picture where we can see some resemblance with the Eden model:

and here is a picture from further away where we can see local resemblance with DLA:

see also this zoom in black and white:

Needless to say, nothing is known about this model.

**Internal Diffusion Limited Aggregation (IDLA)**

Finally the IDLA model is yet another modification of DLA, where instead of starting the random walk from infinity one starts it from the origin. Perhaps surprisingly, and on the contrary to everything discussed so far, we know quite a lot about this model! Its limit shape is an actual honest Euclidean ball, see this paper by Lawler, Bramson and Griffeath. In fact we even know that the average fluctuation from the aggregate around its limit is of constant order, see this paper by Jerison, Levine and Sheffield (information about the distribution of these fluctuations is also provided!).

Writing this blog post was quite a bit of fun, and I thank Ronen Eldan, Laura Florescu, Shirshendu Ganguly, and Yuval Peres from whom I learned everything discussed here. To conclude the post here are some intriguing pictures from variants of the above model that I cooked up (unfortunately I’m not sure the models are very interesting though):

]]>

**The Problem and the Monte Carlo Method**

Let us fix some notation and look at the simplest possible setting. We have a function , that maps the real interval to the reals, and we want to know

We will estimate this integral with the average , where is a sequence of numbers in . The error of this estimate is

And here is the main problem I will talk about in this post:

How do we choose a sequence of points in so that the average approximates the integral as closely as possible?

Intuitively, for larger the approximation will be better, but what is the best rate we can achieve? Notice that we want a single sequence, so that if we want a more accurate approximation, we just take a few more terms and re-normalize, rather than start everything from scratch. The insight of the Monte Carlo method (surely familiar to every reader of this blog) is to take each to be a fresh random sample from . Then for any , the expectation of is exactly (from now on I will skip the limits of my integrals: they will all be from to ). The standard deviation is of order

and standard concentration inequalities tell us that, with high probability, will not be much larger than the latter quantity.

**Quasi-Monte Carlo and Discrepancy**

For a fixed function of bounded norm, the Monte Carlo method achieves roughly on the order of . In other words, if we want to approximate our integral to within , we need to take about random samples. It’s clear that in general, even for smooth functions, we cannot hope to average over fewer than points, but is really the best we can do? It turns out that for reasonably nice we can do a lot better using discrepancy. We define the *star discrepancy function* of a sequence as

Notice that this is really just a special case of where is the indicator function of the interval . A beautiful inequality due to Koksma shows that in a sense these are the only functions we need to care about:

is the *total variation* of , a measure of smoothness, and for continuously differentiable functions it is equal to . The important part is that we have bounded the integration error by the product of a term that quantifies how nice is, and a term that quantifies how “random” the sequence is. With this, our task is reduced to finding a sequence with small star discrepancy, hopefully smaller than . This is the essence of the quasi-Monte Carlo method.

**The van der Corput Sequence**

A simple sequence with low star discrepancy was discovered by van der Corput in the beginning of the previous century. Let us write the integer in binary as , i.e. . Then we define to be number we get by flipping the binary digits of around the radix point: , or, in binary, . The *van der Corput sequence* is .

I have plotted the first eight terms of the van der Corput sequence on the left in the above picture: the index is on the -axis and the value on the -axis. The terms alternate between and ; they also visit each of , , , exactly once before they return, and so on. For example, each shaded rectangle on the right in the above picture contains exactly one point (the rectangles are open on the top). The key property of the van der Corput sequence then is that if and only if . So for any such *dyadic interval*, the discrepancy is at most : the number of integers less than such that is either or . We can greedily decompose an interval into dyadic intervals plus a leftover interval of length ; therefore the *star discrepancy of the van der Corput sequence is *. Remember that, together with Koksma’s inequality, this means that we can estimate the integral of any function with bounded variation with error , which, for sufficiently smooth , is almost quadratically better than the Monte Carlo method! And with a deterministic algorithm, to boot. This was not that hard, so maybe we can achieve the ultimate discrepancy bound ? This is the question (asked by van der Corput) which essentially started discrepancy theory. The first proof that is not achievable was given by van Aardenne-Ehrenfest. Klaus Roth simplified her bound and strengthened it to using a brilliant proof based on Haar wavelets. Schmidt later proved that van der Corput’s bound is assymptotically the best possible.

**Higher Dimension, Other Measures, and Combinatorial Discrepancy**

Quasi-Monte Carlo methods are used in real world applications, for example in quantitative finance, because of the better convergence rates they offer. But there are many complications that arise in practice. One issue is that we usually need to estimate integrals of *high-dimensional functions*, i.e. functions of a large number of variables. The Koksma inequality generalizes to higher dimensions (the generalization is known as the Koksma-Hlawka inequality), but we need to redefine both discrepancy and total variation for that purpose. The star discrepancy of a sequence of -dimensional points measures the worst-case absolute difference between the -dimensional volume (Lebesgue measure) of any anchored box and the fraction of points in the sequence that fall in the box. The generalization of total variation is the Hardy-Krause total variation. Naturally, the best achievable discrepancy increases with dimension, while the class of functions of bounded total variation becomes more restrictive. However, we do not even know what is the best achievable star discrepancy for or higher dimensional sequences! We know that no -dimensional sequence has discrepancy better than , where is some constant that goes to with . The van der Corput construction generalizes to higher dimensions and gives sequences with discrepancy (the implied constants here and in the lower bounds depend on ). The discrepancy theory community refers to closing this significant gap as “The Great Open Problem”.

Everything so far was about integration with respect to the Lebesgue measure, but in practice we are often interested in a different measure space. We could absorb the measure into the function to be integrated, but this can affect the total variation badly. We could do a change of variables, but, unless we have a nice product measure, this will result in a notion of discrepancy in which the test sets are not boxes anymore. Maybe the most natural solution is to redefine star discrepancy with respect to the measure we care about. But how do we find a low-discrepancy sequence with the new definition? It turns out that **combinatorial discrepancy** is very helpful here. A classical problem in combinatorial discrepancy, Tusnady’s problem, asks for is the smallest function such that any set of points in can be colored with red and blue so that in any axis-aligned box the absolute difference between the number of red and the number of blue points is at most (see this post for a generalization of this problem). A general transference theorem in discrepancy theory shows that *for any probability measure in * there exists a sequence with star discrepancy at most . The best bound for is , only slightly worse than the best star discrepancy for Lebesgue measure. This transference result has long been seen as purely existential, because most non-trivial results in combinatorial discrepancy were not constructive, but recently we have seen amazing progress in algorithms for minimizing combinatorial discrepancy. While even with these advances we don’t get sequences that are nearly as explicit as the van der Corput sequence, there certainly is hope we will get there.

**Conclusion**

I have barely scratched the surface of Quasi Monte Carlo methods and geometric discrepancy. Koksma-Hlawka type inequalities, discrepancy with respect to various test sets and measures, combinatorial discrepancy are each a big topic in itself. The sheer breadth of mathematical tools that bear on discrepancy questions is impressive: diophantine approximation to construct low discrepancy sequences, reproducing kernels in Hilbert spaces to prove Koksma-Hlawka inequalities, harmonic analysis to prove discrepancy lower bounds, convex geometry for upper and lower bounds in combinatorial discrepancy. Luckily, there are some really nice references available. Matousek has a very accessible book on geometric discrepancy. Chazelle focuses on computer science applications. A new collection of surveys edited by Chen, Srivastav, and Travaglini has many of the latest developments.

]]>We prove that the Fenchel dual of the log-Laplace transform of the uniform measure on a convex body in is a -self-concordant barrier. This gives the first construction of a universal barrier for convex bodies with optimal self-concordance parameter. The proof is based on basic geometry of log-concave distributions, and elementary duality in exponential families.

Let me briefly put this in context. As you know if you are a reader of this blog, Interior Point Methods are based on self-concordant barriers, and a basic result in this theory is Nesterov and Nemirovski’s construction of a *universal self-concordant barrier* whose self-concordance parameter is always , see this blog post for instance. As I said at the time of writing the latter post, “this is a difficult theorem, which we state without a proof”. Similarly, in James Renegar’s book on IPM (which I highly recommend) he qualifies this as “a most impressive and theoretically important result”, but he also says “I have yet to find a relatively transparent proof of this result, and hence a proof is not contained in this book”. We hope our paper remedies this issue. In fact, our construction, which is quite different from the Nesterov-Nemirovski’s barrier, has a few advantages:

– The new barrier has a very simple interpretation as the differential entropy of a certain element in a canonical exponential family on the convex body of interest, hence the name *entropic barrier*.

– Its self-concordance parameter is optimal (up to the second order term). Indeed Nesterov and Nemirovski proved that on a simplex, the self-concordance parameter is at least , and we obtain a parameter for any convex body.

– The proof is reasonably easy. For instance the self-concordance follows immediately from the fact that higher order moments of a log-concave distribution are controlled by the second order moment. (In fairness getting the tight constant requires a little bit of work, but proving a bound of is simpler.)

– Mirror Descent with the entropic barrier as a mirror map is equivalent to Cover’s continuous exponential weights, which is kind of interesting.

I would like to conclude with a comment on a result by Roland Hildebrand: he proves that for convex cones, there exists a self-concordant barrier with parameter smaller than (yes I mean ). This is quite amazing, and better than what we obtain since we get . However his result has two caveats: (i) as far as I understand his barrier is defined only implicitely, as the unique convex solution to a certain PDE, and (ii) while convex cones are “universal” for convex optimization, there are actually other applications where it is important to have barriers on convex bodies, see for instance some of the papers by Sasha Rakhlin. [Edit: thanks to an email by Francois Glineur we realized that a side result of our analysis is an alternative proof of Hildebrand’s bound for homogeneous cones by using a deep result of Guler. This is very mysterious and we don’t quite understand the full extent of the implication of this yet.]

]]>The topic of this post is the reason why the blog has been silent for the past 3 months: I have just uploaded three new network papers, written with amazing co-authors (Luc Devroye, Jian Ding, Ronen Eldan, Gabor Lugosi, Elchanan Mossel, and Miklos Racz), and which can be found here, here, and here. The overall goal of these works is to realize (a version of) the vision that Nati Linial presented in a public lecture at the Simons Institute in Berkeley about a year ago. As Nati puts it, there is a need for a statistical theory on graphs, and specifically he writes that we should “Develop a battery of generative models of graphs and methods to recover the appropriate model from the input graph”. Obviously this type of question has already been looked at by statisticians, but somehow I feel like they have been shy in the models and questions that they consider. I think that there is a huge opportunity to look at more exotic (yet practically relevant) estimation problems with network data. To simplify, and get at the heart of the matter, I will essentially discuss testing problems rather than estimation.

**Is there geometry in my network?**

In the space of testing problems on random graphs, the king of the hill is testing for *community structure*. A precise hypothesis testing problem considered by Ery Arias-Castro and Nicolas Verzelen (see here and here) is the following: Under the null hypothesis, the observed graph on vertices has been generated by the standard Erdos-Renyi random graph , where each edge appears independently with probability . Under the alternative, comes from the model which is similar to except that there is a subset of vertices (the *community*) chosen uniformly at random and such that the connection probability between two vertices from that subset is instead of . The case and corresponds to the now famous Planted Clique (PC) problem. In PC it is easy to see that the information theoretic limit for testability is when is of order (use for instance this), but surprisingly we do not know any polynomial-time test when . Bridging this gap is a major open problem.

Testing for community structure is of course very important in practice (and it’s also a beautiful mathematical question), but it seems a bit silly to restrict all the attention to this single question. In my joint work with Jian, Ronen and Miki we propose to test for *geometric structure*. This is also quite important in practice, as learning representations for the vertices of a graph is a fundamental primitive to many network analysis techniques. The abstract of our paper reads as follows, and I refer you to the paper itself for more details:

We study the problem of detecting the presence of an underlying high-dimensional geometric structure in a random graph. Under the null hypothesis, the observed graph is a realization of an Erdos-Renyi random graph . Under the alternative, the graph is generated from the model, where each vertex corresponds to a latent independent random vector uniformly distributed on the sphere , and two vertices are connected if the corresponding latent vectors are close enough. In the dense regime (i.e., is a constant), we propose a near-optimal and computationally efficient testing procedure based on a new quantity which we call signed triangles. The proof of the detection lower bound is based on a new bound on the total variation distance between a Wishart matrix and an appropriately normalized GOE matrix. In the sparse regime, we make a conjecture for the optimal detection boundary. We conclude the paper with some preliminary steps on the problem of estimating the dimension in .

**Where did my network come from?**

The two other papers (1, 2) are follow-ups on the project that I described a few months ago in this blog post. In a nutshell the goal was to understand if the Preferential Attachment model depends on its initial condition. See for example these beautiful pictures by Igor Kortchemski of the Preferential Attachment tree on vertices with different seeds:

(click here to see the seeds for the above pictures, and see here and here for pictures with other seeds). With Elchanan and Miki we conjectured that any initial condition leads to a different model, and we were able to partially prove this conjecture. The full conjecture was proved in a beautiful follow-up paper by a group of fellow French, Nicolas Curien, Thomas Duquesne, Igor Kortchemski, and Ioan Manolescu. Using their new proof technique (but with a different statistic) we (Ronen, Elchanan, Miki, and I) were then able to extend the theorem to the Uniform Attachment model, in which case the result is perhaps even more surprising (in fact I was originally convinced that the seed could not possibly have an influence in the Uniform Attachment model!). The paper can be found here.

The *Seed Theorem* emerging from these works opens up the problem of actually *finding* the seed. This is the problem we looked at with Luc and Gabor (in the special case where the seed is a single vertex), and the abstract of the paper reads as follows:

We investigate algorithms to find the first vertex in large trees generated by either the uniform attachment or preferential attachment model. We require the algorithm to output a set of vertices, such that, with probability at least , the first vertex is in this set. We show that for any , there exist such algorithms with independent of the size of the input tree. Moreover, we provide almost tight bounds for the best value of as a function of . In the uniform attachment case we show that the optimal is subpolynomial in , and that it has to be at least superpolylogarithmic. On the other hand, the preferential attachment case is exponentially harder, as we prove that the best is polynomial in . We conclude the paper with several open problems.

**Open problems**

The four papers (1, 2, 3, 4) contain about a dozen open problems, and we could have easily extended the list to twenty open problems (for example I have added a few open problems in my talk at Oberwolfach two weeks ago, see here for Louigi Addario-Berry‘s notes). Can you solve one of them? Or even better, can you propose new interesting graph hypothesis testing problems?

]]>**Discrepancy theory**

Consider a large finite set of vertices , and a size- set of subsets of vertices (in other words is an hypergraph). For sake of simplicity we will assume here that elements of are also of size . We are now interested in the following combinatorial optimization problem:

In words, one is looking for a partitioning of the vertices, so as to have the hyperedges as balanced as possible.

Alright, so let’s try something simple, just randomly partition the vertices: clearly a simple union bounds shows that the obtained objective value in this case is of order . Denote (for *Discrepancy*) the smallest objective value (in particular we just saw that ). A beautiful result of Joel Spencer shows that one can *always* do much better than random partitioning:

Theorem(Spencer’s six deviations, 1985): .

We will now see a splendid (partial) proof of this result. Let be the Gaussian measure in (in the following we will take ). First let me remind you of a basic fact about this measure, and a related conjecture. A set of the form , for some , is called a *slab*.

Theorem(Sidak, 1967): Let be a symmetric convex set and be a slab, then

Obviously there is equality if and are two orthogonal slabs, and the theorem says (in particular) that an angle between the slabs would imply positive correlation.

Conjecture(Gaussian correlation): Let and be two symmetric convex sets, then

Ok, now back to the proof of Spencer’s theorem. First, let’s rewrite things suggestively in terms of the slabs , . We want to show that there exists such that . Using Sidak’s theorem one clearly has (with being roughly like ). From there it is now a fairly short route to show that, if (say), then the intersection of with must be non-empty. Ronen showed me a non-trivial (and algorithmically non-efficient) 5 lines argument for this but I think that it’s yet unpublished work so I won’t reproduce it here. Another proof of this, which yields an efficient algorithm for finding a point in the intersection, is given in this very nice paper of Lovett and Meka.

**Extensions**

In what we discussed so far the underlying hypergraph was completely arbitrary. For some specific graphs one can clearly improve the bound on . Indeed if all hyperedges are disjoint, then . More interestingly, Beck and Fiala showed in 1981 that, if each vertex appears in at most hyperedges, then . They also conjectured that the correct bound should be . In 1998 Banaszczyk showed a bound of using the following theorem (which is a variant of the result mentioned above):

Theorem(Banaszczyk, 1998): Let be a convex set such that , and such that . Then there exists such that .

The longstanding Komlos’ conjecture says that in fact this holds for (despite the fact that the Gaussian measure of this set is ).

Finally let me mention another open problem, which is the matrix version of Spencer’s six deviations, see this blog post by Raghu Meka for details.

]]>

Let be a positive integer. A partition of is a multiset of positive integers such that the sum of its elements is equal to (for example is a partition of ). The partition function is defined as the number of partitions of . The amazing result that I want to tell you about is the formula for the asymptotic equivalent of . Before giving away the formula let’s try to get some intuition about the order of magnitude one can expect. For this let me first look at the simpler quantity , defined as the number of multiset of with elements (for example ). With the stars and bars argument (thanks to Luc Devroye for reminding me about this elementary combinatorial technique!) one can easily see that . Moreover it is also easy to see that there is an injection from multisets of with elements to partitions of (observe that the sum of the elements of such a multiset is necessarily smaller than ). Thus

A more involved argument, based on Young Diagram representation of partitions, shows that (don’t quote me on the , I think it’s correct but I have only rough calculations here).

Now here we go for the asymptotic formula, discovered by Hardy and Ramanujan in 1918:

In my opinion this is a beautiful connection between , , and a basic property of integers. The proof is based on the circle method, an elementary technique in complex analysis (see here for the details).

]]>The point of this post is to advertise the lecture notes of my friend (and colleague) Ramon van Handel. These notes cover all the basics of modern high dimensional probability. Acquaintance with this material is extremely useful in all the fields that I’m interested in (machine learning, statistics, optimization, and theoretical computer science). It is the first time that I see this material presented in such a cohesive manner, and it is an excellent companion to the book of Boucheron, Lugosi and Massart. Last but not least Ramon is an amazing mathematical writer (for instance if you want to learn about filtering I highly recommend his lecture notes on Hidden Markov Models).

]]>This monograph presents the main mathematical ideas in convex optimization. Starting from the fundamental theory of black-box optimization, the material progresses towards recent advances in structural optimization and stochastic optimization. Our presentation of black-box optimization, strongly influenced by the seminal book of Nesterov, includes the analysis of the Ellipsoid Method, as well as (accelerated) gradient descent schemes. We also pay special attention to non-Euclidean settings (relevant algorithms include Frank Wolfe, Mirror Descent, and Dual Averaging) and discuss their relevance in machine learning. We provide a gentle introduction to structural optimization with FISTA (to optimize a sum of a smooth and a simple non-smooth term), Saddle-Point Mirror Prox (Nemirovski’s alternative to Nesterov’s smoothing), and a concise description of Interior Point Methods. In stochastic optimization we discuss Stochastic Gradient Descent, mini-batches, Random Coordinate Descent, and sublinear algorithms. We also briefly touch upon convex relaxation of combinatorial problems and the use of randomness to round solutions, as well as random walks based methods.

]]>