3 papers
cs.LG2026
Improved high-dimensional estimation with Langevin dynamics and stochastic weight averaging
Stanley Wei, Alex Damian, Jason D. Lee
Significant recent work has studied the ability of gradient descent to recover a hidden planted direction in different high-dimensional settings, including t…
cs.LG2025
Understanding Optimization in Deep Learning with Central Flows
Jeremy M. Cohen, Alex Damian, Ameet Talwalkar +2
Traditional theories of optimization cannot describe the dynamics of optimization in deep learning, even in the simple setting of deterministic training. The challenge is that opti…
cs.LG2025
The Generative Leap: Sharp Sample Complexity for Efficiently Learning Gaussian Multi-Index Models
Alex Damian, Jason D. Lee, Joan Bruna
In this work we consider generic Gaussian Multi-index models, in which the labels only depend on the (Gaussian) -dimensional inputs through their projection onto a low-dimension…