2 citations · 5 across the 13 of their papers we have counts for
14 papers
LinearPFN: Amortized Variable Selection for Linear Models with Interactions
Louis Schiekiera, Max Zimmer, Christophe Roux +3
Spike-and-slab regression is a standard Bayesian formulation of variable selection: it returns a posterior distribution over which candidate effects are active rather than a single…
Curvature-Dependent Lower Bounds for Frank-Wolfe
Jannis Halbey, Christophe Roux, Sebastian Pokutta
The Frank-Wolfe algorithm achieves a convergence rate of for smooth convex optimization over compact convex domains, accelerating to when bo…
The Agentic Researcher: A Practical Guide to AI-Assisted Research in Mathematics and Machine Learning
Max Zimmer, Nico Pelleriti, Christophe Roux +1
AI tools and agents are reshaping how researchers work, from proving theorems to training neural networks. Yet for many, it remains unclear how these tools fit into everyday resear…
From Associations to Activations: Comparing Behavioral and Hidden-State Semantic Geometry in LLMs
Louis Schiekiera, Max Zimmer, Christophe Roux +2
We investigate the extent to which an LLM's hidden-state geometry can be recovered from its behavior in psycholinguistic experiments. Across eight instruction-tuned transformer mod…
Lower Bounds for Frank-Wolfe on Strongly Convex Sets
Jannis Halbey, Daniel Deza, Max Zimmer +3
We present a constructive lower bound of for Frank-Wolfe (FW) when both the objective and the constraint set are smooth and strongly convex, showing that…
SparseSwaps: Tractable LLM Pruning Mask Refinement at Scale
Max Zimmer, Christophe Roux, Moritz Wagner +2
The resource requirements of neural networks can be significantly reduced through pruning - the removal of seemingly less important parameters. However, for LLMs, full retraining t…
Don't Be Greedy, Just Relax! Pruning LLMs via Frank-Wolfe
Christophe Roux, Max Zimmer, Alexandre d'Aspremont +1
Pruning is a common technique to reduce the compute and storage requirements of Neural Networks. While conventional approaches typically retrain the model to recover pruning-induce…
A Free Lunch in LLM Compression: Revisiting Retraining after Pruning
Moritz Wagner, Christophe Roux, Max Zimmer +1
Post-training pruning can substantially reduce LLM inference costs, but it often degrades quality unless the remaining weights are adapted. Since global retraining is expensive at…
Implicit Riemannian Optimism with Applications to Min-Max Problems
Christophe Roux, David Martínez-Rubio, Sebastian Pokutta
We introduce a Riemannian optimistic online learning algorithm for Hadamard manifolds based on inexact implicit updates. Unlike prior work, our method can handle in-manifold constr…
Convergence and Trade-Offs in Riemannian Gradient Descent and Riemannian Proximal Point
David Martínez-Rubio, Christophe Roux, Sebastian Pokutta
In this work, we analyze two of the most fundamental algorithms in geodesically convex optimization: Riemannian gradient descent and (possibly inexact) Riemannian proximal point. W…
On the Byzantine-Resilience of Distillation-Based Federated Learning
Christophe Roux, Max Zimmer, Sebastian Pokutta
Federated Learning (FL) algorithms using Knowledge Distillation (KD) have received increasing attention due to their favorable properties with respect to privacy, non-i.i.d. data a…
Accelerated Methods for Riemannian Min-Max Optimization Ensuring Bounded Geometric Penalties
David Martínez-Rubio, Christophe Roux, Christopher Criscitiello +1
In this work, we study optimization problems of the form , where is defined on a product Riemannian manifold and i…
Efficient Online-Bandit Strategies for Minimax Learning Problems
Christophe Roux, Elias Wirth, Sebastian Pokutta +1
Several learning problems involve solving min-max problems, e.g., empirical distributional robust learning or learning with non-standard aggregated losses. More specifically, these…
Linear Bandits on Uniformly Convex Sets
Thomas Kerdreux, Christophe Roux, Alexandre d'Aspremont +1
Linear bandit algorithms yield pseudo-regret bounds on compact convex action sets and two types of structural assu…