53 citations · 420 across the 50 of their papers we have counts for
Showing 2022Show all
2 papers · 1 filter
cs.LG2022
A Moment-Matching Approach to Testable Learning and a New Characterization of Rademacher Complexity
Aravind Gollakota, Adam R. Klivans, Pravesh K. Kothari
A remarkable recent paper by Rubinfeld and Vasilyan (2022) initiated the study of \emph{testable learning}, where the goal is to replace hard-to-verify distributional assumptions (…
cs.LG2022★ 6 cited
Hardness of Noise-Free Learning for Two-Hidden-Layer Neural Networks
Sitan Chen, Aravind Gollakota, Adam R. Klivans +1
We give superpolynomial statistical query (SQ) lower bounds for learning two-hidden-layer ReLU networks with respect to Gaussian inputs in the standard (noise-free) model. No gener…