Author Archives: Sebastien Bubeck

COLT 2018 call for papers

Philippe Rigollet and myself will be the program chairs for this year’s edition of COLT. It will be in Stockholm in July, which I hear is absolutely gorgeous at that time of the year. We also have a fantastic lineup … Continue reading

Posted in Conference/workshop | Leave a comment

Michael B. Cohen

This is an incredibly difficult post to write. Michael Benjamin Cohen, an amazing student and person passed away this week in Berkeley. Below is the official MSR statement (where he spent the summer together with many friends) and some personal … Continue reading

Posted in Uncategorized | 7 Comments

Smooth distributed convex optimization

A couple of months ago we (Kevin Scaman, Francis Bach, Yin Tat Lee, Laurent Massoulie and myself) uploaded a new paper on distributed convex optimization. We came up with a pretty clean picture for the optimal oracle complexity of this … Continue reading

Posted in Optimization | Leave a comment

COLT 2017 accepted papers

The list of accepted papers at COLT 2017 has been published and it looks particularly good (see below with links to arxiv version)! The growth trend of previous years continues with 228 submissions (14% increase from 2016) and 73 accepted … Continue reading

Posted in Conference/workshop | 1 Comment

Discrepancy algorithm inspired by gradient descent and multiplicative weights; after Levy, Ramadas and Rothvoss

A week or so ago at our Theory Lunch we had the pleasure to listen to Harishchandra Ramadas (student of Thomas Rothvoss) who told us about their latest discrepancy algorithm. I think the algorithm is quite interesting as it combines … Continue reading

Posted in Theoretical Computer Science | 1 Comment

New journal: Mathematical Statistics and Learning

I am thrilled to announce the launch of a new journal, “Mathematical Statistics and Learning”, to be edited be the European Mathematical Society. The goal of the journal is be the natural home for the top works addressing the mathematical … Continue reading

Posted in Announcement | 1 Comment

STOC 2017 accepted papers

The list of accepted papers to STOC 2017 has just been released. Following the trend in recent years there are quite a few learning theory papers! I have already blogged about the kernel-based convex bandit algorithm; as well as the … Continue reading

Posted in Conference/workshop, Theoretical Computer Science | 2 Comments

Guest post by Miklos Racz: Confidence sets for the root in uniform and preferential attachment trees

In the final post of this series (see here for the previous posts) we consider yet another point of view for understanding networks. In the previous posts we studied random graph models with community structure and also models with an … Continue reading

Posted in Probability theory, Random graphs | 1 Comment

Geometry of linearized neural networks

This week we had the pleasure to host Tengyu Ma from Princeton University who told us about the recent progress he has made with co-authors to understand various linearized versions of neural networks. I will describe here two such results, … Continue reading

Posted in Machine learning, Optimization | 2 Comments

Local max-cut in smoothed polynomial time

Omer Angel, Yuval Peres, Fan Wei, and myself have just posted to the arXiv our paper showing that local max-cut is in smoothed polynomial time. In this post I briefly explain what is the problem, and I give a short … Continue reading

Posted in Optimization, Probability theory | 2 Comments