3 papers
cs.LG2026
Deep Networks Learn Deep Hierarchical Models
Amit Daniely
We consider supervised learning with labels and show that layerwise SGD on residual networks can efficiently learn a class of hierarchical models. This model class assumes the…
cs.LG2024
RedEx: Beyond Fixed Representation Methods via Convex Optimization
Amit Daniely, Mariano Schain, Gilad Yehudai
Optimizing Neural networks is a difficult task which is still not well understood. On the other hand, fixed representation methods such as kernels and random features have provable…
cs.LG2023
Locally Optimal Descent for Dynamic Stepsize Scheduling
Gilad Yehudai, Alon Cohen, Amit Daniely +3
We introduce a novel dynamic learning-rate scheduling scheme grounded in theory with the goal of simplifying the manual and time-consuming tuning of schedules in practice. Our appr…