Y. Carmon

activity

20132026

most citedModel soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time

206 citations · 808 across the 40 of their papers we have counts for

collaborators

Showing 2025 · math.OCShow all

1 paper · 2 filters

math.OC2025

Convergence of Clipped SGD on Convex $(L_{0}, L_{1})$ -Smooth Functions

Ofir Gaash, Kfir Yehuda Levy, Yair Carmon

We study stochastic gradient descent (SGD) with gradient clipping on convex functions under a generalized smoothness assumption called $(L_{0}, L_{1})$ -smoothness. Using gradient clippi…

Convergence of Clipped SGD on Convex (L0​,L1​)-Smooth Functions

Convergence of Clipped SGD on Convex $(L_{0}, L_{1})$ -Smooth Functions