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 2016Show all

3 papers · 1 filter

math.OC2016

Gradient Descent Finds the Cubic-Regularized Non-Convex Newton Step

Yair Carmon, John C. Duchi

We consider the minimization of non-convex quadratic forms regularized by a cubic term, which exhibit multiple saddle points and poor local minima. Nonetheless, we prove that, unde…

math.OC2016★ 53 cited

Accelerated Methods for Non-Convex Optimization

Yair Carmon, John C. Duchi, Oliver Hinder +1

We present an accelerated gradient method for non-convex optimization problems with Lipschitz continuous first and second derivatives. The method requires time $O(ε^{-7/4} \log(1/…

stat.ML2016★ 143 cited

No bad local minima: Data independent training error guarantees for multilayer neural networks

Daniel Soudry, Yair Carmon

We use smoothed analysis techniques to provide guarantees on the training loss of Multilayer Neural Networks (MNNs) at differentiable local minima. Specifically, we examine MNNs wi…