hugorichard.bsky.social
@hugorichard.bsky.social
Researcher at Criteo. Interested in Bandits, Privacy, Competitive Analysis, Reinforcement Learning.
https://hugorichard.github.io/
Reposted
I want to advertise some relatively recent work which I really like, and have been fortunate to play a small role in.

The paper is titled "A New Proof of Sub-Gaussian Norm Concentration Inequality" (arxiv.org/abs/2503.14347), led by Zishun Liu and Yongxin Chen at Georgia Tech.
August 19, 2025 at 8:28 AM
Reposted
I'm going to slowly repost my math notes from the other site🐦 here🦋; it's the only thing I posted over there that I think may have some long-term value & worth not deleting.

These started out as notes for myself, but people seem to appreciate them. 😅

I'll keep track of all of them in this thread.
November 14, 2024 at 5:18 PM
Reposted
JOB OPENING at University of Bristol:
-- Lecturer in Statistics or Machine Learning
-- (x 2 positions available)
-- application deadline: 31 March, 2025

Details at www.bristol.ac.uk/jobs/find/de...

Come join us!
March 5, 2025 at 3:01 PM
Reposted
New preprint!

This is a hardcore technical paper on Thompson sampling - as a strategy for the so-called online learning game.

I think it's one of the most long-term important things I have ever worked on due to what it makes possible.

That needs explaining: thread below!

arxiv.org/abs/2502.14790
An Adversarial Analysis of Thompson Sampling for Full-information Online Learning: from Finite to Infinite Action Spaces
We develop an analysis of Thompson sampling for online learning under full feedback - also known as prediction with expert advice - where the learner's prior is defined over the space of an adversary'...
arxiv.org
February 21, 2025 at 8:57 PM
Reposted
What are the minimal supervised learning primitives required to perform RL efficiently?

New paper led by my amazing intern Dhruv Rohatgi:

Necessary and Sufficient Oracles: Toward a Computational Taxonomy for Reinforcement Learning

arxiv.org/abs/2502.08632

1/
February 20, 2025 at 11:39 PM
Reposted
🏹 Two permanent Lecturer/Senior Lecturer/Reader positions open at @uofglasgow.bsky.social in #AI & #MachineLearning. Topics can include Science & Engineering, Probabilistic Models, Active Inference, Causal ML, & AI/ML in Dynamic/Control Systems. More info: bit.ly/42Teety
Lecturer / Senior Lecturer / Reader in Artificial Intelligence / Machine Learning
Job Purpose   The University of Glasgow, established in 1451, is a member of the UK's Russell Group of leading universities. The University is committed to enhancing its position as one of the worl...
bit.ly
February 13, 2025 at 3:20 PM
Reposted
Talagrand's inequality is a probabilistic isoperimetric inequality that allows to derive a concentration inequality for the median. This is an instance of "concentration of measure" that made him win the Abel Prize in 2024. http://numdam.org/item/PMIHES_1995__81__73_0.pdf
February 11, 2025 at 6:00 AM
Reposted
Michael Jordan's talk on the multi-agent and micro-econ perspective on AI and how we need a new vision of the future is killer:
www.youtube.com/live/W0QLq4q...
AI, Science and Society Conference - AI ACTION SUMMIT - DAY 1
YouTube video by IP Paris
www.youtube.com
February 9, 2025 at 5:32 PM
Nice to see that more people are joining Bluesky. Let me advertize the work of @corentin-pla.bsky.social on mean estimation under user-level local differential privacy. In this setting, users can have more than one data sample.
January 31, 2025 at 7:06 AM
Reposted
Live! Keynote talk by Arnaud Doucet
From Diffusion Models to Schrödinger Bridges
West Exhibition Hall C, B3
https://buff.ly/4ga9GD7
December 12, 2024 at 10:48 PM