Search Results for author:
Found 4 papers, 1 papers with code
A Theory of Non-Linear Feature Learning with One Gradient Step in Two-Layer Neural Networks
However, with a constant gradient descent step size, this spike only carries information from the linear component of the target function and therefore learning non-linear components is impossible.
Demystifying Disagreement-on-the-Line in High Dimensions
Evaluating the performance of machine learning models under distribution shift is challenging, especially when we only have unlabeled data from the shifted (target) domain, along with labeled data from the original (source) domain.
Information-Theoretic Analysis of Minimax Excess Risk
We consider the frequentist problem of minimax excess risk as a zero-sum game between the algorithm designer and the world.
Rate-Distortion Analysis of Minimum Excess Risk in Bayesian Learning
For the upper bound, the optimization is further constrained to use $R$ bits from the training set, a setting which relates MER to information-theoretic bounds on the generalization gap in frequentist learning.
