collaborators

5 papers

cs.LG2026

Sharp Capacity Scaling of Spectral Optimizers in Learning Associative Memory

Juno Kim, Eshaan Nichani, Denny Wu +2

Spectral optimizers such as Muon have recently shown strong empirical performance in large-scale language model training, but the source and extent of their advantage remain poorly…

cs.CL2025

Emergence of Linear Truth Encodings in Language Models

Shauli Ravfogel, Gilad Yehudai, Tal Linzen +2

Recent probing studies reveal that large language models exhibit linear subspaces that separate true from false statements, yet the mechanism behind their emergence is unclear. We…

cs.LG2025

Level Set Teleportation: An Optimization Perspective

Aaron Mishkin, Alberto Bietti, Robert M. Gower

We study level set teleportation, an optimization routine which tries to accelerate gradient descent (GD) by maximizing the gradient norm over a level set of the objective. While t…

cs.LG2025

Distributional Associations vs In-Context Reasoning: A Study of Feed-forward and Attention Layers

Lei Chen, Joan Bruna, Alberto Bietti

Large language models have been successful at tasks involving basic forms of in-context reasoning, such as generating coherent language, as well as storing vast amounts of knowledg…

stat.ML2025

Counterfactual Learning of Stochastic Policies with Continuous Actions

Houssam Zenati, Alberto Bietti, Matthieu Martin +3

Counterfactual reasoning from logged data has become increasingly important for many applications such as web advertising or healthcare. In this paper, we address the problem of le…