collaborators

19 papers

math.OC2026

Finding Simple Proofs for First-Order Optimization

Daniel Berg Thomsen, Manu Upadhyaya, Baptiste Goujaud +2

Progress in mathematics often requires more than a certificate of truth: it requires proof structures that are transparent, checkable, and reusable. Automated systems can increasin…

stat.ML2026

Self-Organized Conformal Prediction: Reducing Regional Coverage Gaps with Unsupervised Group Discovery

Louis Berthier, Ahmed Shokry, Maxime Moreaud +2

Conformal prediction guarantees marginal coverage, but pooled calibration averages over heterogeneous regions and can mask regional undercoverage in safety-critical subgroups. We i…

cs.LG2026

A Tight Theory of Error Feedback Algorithms in Distributed Optimization

Daniel Berg Thomsen, Adrien Taylor, Aymeric Dieuleveut

Communication costs are a major bottleneck in distributed learning and first-order optimization. A common approach to alleviate this issue is to compress the gradient information e…

math.OC2026

An optimal first-order method for smooth and strongly convex composite optimization and its stationary limit

Manu Upadhyaya, Daniel Berg Thomsen, Aymeric Dieuleveut +1

We introduce Prox-ITEM, an optimal proximal gradient method for minimizing , where is smooth and strongly convex, and is convex, proper, and lower semicontinuous. In t…

cs.LG2026

Humanity's Last Exam

Long Phan, Alice Gatti, Ziwen Han +1144

Benchmarks are important tools for tracking the rapid advancements in large language model (LLM) capabilities. However, benchmarks are not keeping pace in difficulty: LLMs now achi…

cs.LG2026

From Inexact Gradients to Byzantine Robustness: Acceleration and Optimization under Similarity

Renaud Gaucher, Aymeric Dieuleveut, Hadrien Hendrikx

Standard federated learning algorithms are vulnerable to adversarial nodes, a.k.a. Byzantine failures. To solve this issue, robust distributed learning algorithms have been develop…