On the Computational Landscape of Replicable Learning
We study computational aspects of algorithmic replicability, a notion of stability introduced by
Impagliazzo, Lei, Pitassi, and Sorrell [2022]. Motivated by a recent line of work that …
Impagliazzo, Lei, Pitassi, and Sorrell [2022]. Motivated by a recent line of work that …
Uniformity Testing over Hypergrids with Subcube Conditioning
X Chen, C Marcussen - Proceedings of the 2024 Annual ACM-SIAM …, 2024 - SIAM
We give an algorithm for testing uniformity of distributions supported on hypergrids [m
1]×···×[mn], which makes many queries to a subcube conditional sampling oracle with m …
1]×···×[mn], which makes many queries to a subcube conditional sampling oracle with m …
New computational and statistical characterizations of neural network learning
A Gollakota - 2023 - repositories.lib.utexas.edu
A foundational goal of machine learning theory is to characterize the inherent computational
and statistical complexity of some of the most basic tasks in machine learning. In this thesis …
and statistical complexity of some of the most basic tasks in machine learning. In this thesis …