2 papers
cs.LG2023
Outliers with Opposing Signals Have an Outsized Effect on Neural Network Optimization
Elan Rosenfeld, Andrej Risteski
We identify a new phenomenon in neural network optimization which arises from the interaction of depth and a particular heavy-tailed structure in natural data. Our result offers in…
stat.ML2023
(Almost) Provable Error Bounds Under Distribution Shift via Disagreement Discrepancy
Elan Rosenfeld, Saurabh Garg
We derive an (almost) guaranteed upper bound on the error of deep neural networks under distribution shift using unlabeled test data. Prior methods either give bounds that are vacu…