← Search

Haixiang Sun

2 accepted papers

2023

Alternating Differentiation for Optimization Layers

ICLR 2023poster

The idea of embedding optimization problems into deep neural networks as optimization layers to encode constraints and inductive priors has taken hold in recent years. Most existing methods focus on implicitly differentiating Karush–Kuhn–Tucker (KKT) conditions in a way that requires expensive compu…