20 citations · 49 across the 16 of their papers we have counts for
Showing 2021Show all
2 papers · 1 filter
math.OC2021★ 6 cited
Neural Network Training as an Optimal Control Problem: An Augmented Lagrangian Approach
Brecht Evens, Puya Latafat, Andreas Themelis +2
Training of neural networks amounts to nonconvex optimization problems that are typically solved by using backpropagation and (variants of) stochastic gradient descent. In this wor…
math.OC2021★ 12 cited
Bregman Finito/MISO for nonconvex regularized finite sum minimization without Lipschitz gradient continuity
Puya Latafat, Andreas Themelis, Masoud Ahookhosh +1
We introduce two algorithms for nonconvex regularized finite sum minimization, where typical Lipschitz differentiability assumptions are relaxed to the notion of relative smoothnes…