# Author Archives: Sebastien Bubeck

## Theory of Convex Optimization for Machine Learning

I am extremely happy to release the first draft of my monograph based on the lecture notes published last year on this blog. (Comments on the draft are welcome!) The abstract reads as follows: This monograph presents the main mathematical … Continue reading

## COLT 2014 accepted papers

The accepted papers for COLT 2014 have just been posted! This year we had a record number of 140 submissions, out of which 52 were accepted (38 for a 20mn presentation and 14 for a 5mn presentation). In my opinion … Continue reading

## On the influence of the seed graph in the preferential attachment model

The preferential attachment model, introduced in 1992 by Mahmoud and popularized in 1999 by Barabási and Albert, has attracted a lot of attention in the last decade. In its simplest form it describes the evolution of a random tree. Formally we denote by … Continue reading

## Nesterov’s Accelerated Gradient Descent for Smooth and Strongly Convex Optimization

About a year ago I described Nesterov’s Accelerated Gradient Descent in the context of smooth optimization. As I mentioned previously this has been by far the most popular post on this blog. Today I have decided to revisit this post to give a … Continue reading

## COLT deadline next week

COLT deadline is approaching fast, don’t forget to send your awesome learning theory paper(s) before Friday 7th! Also recall that if you get a paper into COLT it will (i) give you an excuse to spend a few days in … Continue reading

## One year of blogging

A year ago I started this blog. I did not expect this experience to be so rewarding. For instance seeing weeks after the weeks the growing interest for the optimization posts gave me the stamina to pursue this endaveor to … Continue reading

## A good NIPS!

This year’s edition of NIPS was a big success. As you probably already know we had the surprise visit of Mark Zuckerberg (see here for the reason behind this visit). More interestingly (or perhaps less interestingly depending on who you are) here … Continue reading

## The hunter and the rabbit

In this post I will tell you the story of the hunter and the rabbit. To keep you interested let me say that in the story we will see a powerful (yet trivial) inequality that I learned today from Yuval … Continue reading

## Guest post by Dan Garber and Elad Hazan: The Conditional Gradient Method, A Linear Convergent Algorithm – Part II/II

The goal of this post is to develop a Conditional Gradient method that converges exponentially fast while basically solving only a linear minimization problem over the domain on each iteration. To this end we consider the following relaxation of the … Continue reading

## Guest post by Dan Garber and Elad Hazan: The Conditional Gradient Method, A Linear Convergent Algorithm – Part I/II

In a previous post Sebastien presented and analysed the conditional gradient method for minimizing a smooth convex function over a compact and convex domain . The update step of the method is as follows, where , . The … Continue reading