Samuel Vaiter retweeted
The alpha version of my new book "Optimal Transport
for Machine Learners" is out, with in particular an online version with interactive figures
gpeyre.com/ot4ml/
A quick remark:
When you use centered finite difference instead of forward or backward difference, the truncation error decreases faster, but I never realized that the roundoff error grows before!
Of course you can always use complex step approximation if you don't like roundoff error and you have stable complex arithmetic :)
xitter.cf/vaiter/status/18330184…
Complex step approximation is a numerical method to approximate the derivative from a single function evaluation using complex arithmetic. It is some kind of “poor man” automatic differentiation. nhigham.com/2020/10/06/what-…
Now accepted at ICML 2026! Congrats to @MagamedTm
🧵 New preprint! "Towards Understanding Steering Strength" with @MagamedTm and D. Garreau
Activation steering is a popular way to control LLM behavior at inference. But how much should you steer? We provide the first theoretical analysis of the steering strength α.
1/7
🧵 New preprint! "Towards Understanding Steering Strength" with @MagamedTm and D. Garreau
Activation steering is a popular way to control LLM behavior at inference. But how much should you steer? We provide the first theoretical analysis of the steering strength α.
1/7
We validate everything empirically on 11 models (GPT-2, Gemma 3, Qwen 3, Llama 2, Mistral 7B) across 8 safety-related concepts. All our theorems are confirmed experimentally.
6/7
TL;DR: Steering strength α has precise, predictable effects on LLM outputs. Understanding these laws may help design better steering strategies.
Paper: arxiv.org/abs/2602.02712
Code: github.com/MagamedT/steering
7/7
Les inscriptions aux journées MODE 2026 à Nice sont désormais ouvertes. Elles se dérouleront du 18 au 20 mars à l'Hôtel Saint-Paul.
Les inscriptions sont ouvertes jusqu'au 1 mars (majoration > 9/02). La deadline pour soumettre une communication est le **15 janvier**.
Pour s'inscrire et pour plus d'informations : mode2026.sciencesconf.org
Les orateurs et oratrices pléniers sont Pierre Ablin, Yann Brenier, Julie Delon, Stéphane Gaubert, Francisco J. Silva Álvarez (prix J.J Moreau) et Irène Waldspurger.
Attention, le nombre de place est limité !
Samuel Vaiter retweeted
🏅Finalist: Gradient Scarcity in Graph Learning with Bilevel Optimization, by Hashem Ghanem, @vaiter, @n_keriven 5/n
openreview.net/forum?id=10YJ…
Samuel Vaiter retweeted
Happy to be at #NeurIPS2025 in San Diego to present our poster ‘Learning Theory for Kernel Bilevel Optimization’ #3005, Fri at 4:30 p.m. Stop by/ping me to chat, especially about statistics, causality, generative models! Let's connect!
Joint w/ E. Pauwels, @vaiter, @MichaelArbel
Les journées SMAI-MODE 2026 auront lieu à Nice du 18 au 20 mars 2026, précédées par un mini-cours les 16/17.
Vous pouvez déposer votre proposition de contrib sur mode2026.sciencesconf.org
Inscription à partir du 1er décembre, fin le 1 mars (tarif majoré à compter du 1 février).