Statistical Learning
Pareto Frontiers in Deep Feature Learning: Data, Compute, Width, and Luck Benjamin L. Edelman
This work investigates how these complexities necessarily arise for feature learning in the presence of computational-statistical gaps.
9602d22a8c791f23f8e4d1398e3fb5be-Paper-Conference.pdf
These theoretical findings are supported by experimental results.
Online Performative Gradient Descent for Learning Nash Equilibria in Decision-Dependent Games Zihan Zhu Duke University Ethan X. Fang Duke University Zhuoran Yang Yale University
We focus on finding the Nash equilibrium of decision-dependent games in the bandit feedback setting.
Fast Exact Leverage Score Sampling from Khatri-Rao Products with Applications to Tensor Decomposition
As a result, it tractably draws samples even when the matrices forming the Khatri-Rao product have tens of millions of rows each.
Mechanic: A Learning Rate Tuner
Modern deep learning is driven by first-order stochastic optimization algorithms.
Mechanic: A Learning Rate Tuner
Modern deep learning is driven by first-order stochastic optimization algorithms.
Generalized Fast Exact Conformalization
It enjoys model-free coverage guarantee regardless of the underlying distribution of the data.
