# Author Archives: Sebastien Bubeck

## Nemirovski’s acceleration

I will describe here the very first (to my knowledge) acceleration algorithm for smooth convex optimization, which is due to Arkadi Nemirovski (dating back to the end of the 70’s). The algorithm relies on a -dimensional plane-search subroutine (which, in … Continue reading

## A short proof for Nesterov’s momentum

Yesterday I posted the following picture on Twitter and it quickly became my most visible tweet ever (by far): I thought this would be a good opportunity to revisit the proof of Nesterov’s momentum, especially since as it … Continue reading

## Remembering Michael

It has been a year since the tragic event of September 2017. We now know what happened, and it is a tremendously sad story of undiagnosed type 1 diabetes. This summer at MSR Michael was still very present in our … Continue reading

## How to generalize (algorithmically)

A couple of months ago I taught an introduction to statistical learning theory. I took inspiration from two very good introductory books on SLT: “Foundations of ML”, and “Understanding Machine Learning: From Theory to Algorithms”. I also covered some classical … Continue reading

## Some updates

The blog has been eerily silent for most of 2018, here is why: The main culprit is definitely the COLT 2018 chairing. This year we received a surprise 50% increase in number of submissions. This is great news for the … Continue reading

## Youtube channel

I just started a youtube channel. The hope is that this will be a companion to the blog. Some of the posts will “graduate” into videos (e.g., the first set of videos will correspond to an expanded version of bandit … Continue reading

## k-server, part 3: entropy regularization for weighted k-paging

If you have been following the first two posts (post 1, post 2), now is time to reap the rewards! I will show here how to obtain a -competitive algorithm for (weighted) paging, i.e., when the metric space corresponds to … Continue reading

## k-server, part 2: continuous time mirror descent

We continue our -server series (see post 1 here). In this post we briefly discuss the concept of a fractional solution for -server, which by analogy with MTS will in fact be a fractional “anti-solution”. Then we introduce the continuous … Continue reading

## k-server, part 1: online learning and online algorithms

The -server problem is a classical and very attractive instance of online decision making. The decisions to be made in this problem are simple: given a requested location in some finite metric space and a fleet of k servers currently sitting … Continue reading

## Algorithms, Machine Learning, and Optimization: we are hiring!

As some of you already know there has been some movement at MSR lately, specifically for the theory group. We have now branched out into two groups, one in Machine Learning and Optimization -MLO- (with Zeyuan Allen-Zhu, myself, Ofer Dekel, … Continue reading