Max Simchowitz

Gradient Descent Only Converges to Minimizers

Jason D. Lee, Max Simchowitz, Michael I. Jordan et al. · Conference on Learning Theory · 2016 · 385 citations

Gradient Descent, Engineering, Machine Learning +4

Low-rank solutions of linear matrix equations via procrustes flow

Stephen Tu, Ross Boczar, Max Simchowitz et al. · 2016 · 145 citations

Low-rank Solutions of Linear Matrix Equations via Procrustes Flow

Stephen Tu, Ross Boczar, Max Simchowitz et al. · arXiv (Cornell University) · 2015 · 143 citations · Full text

Numerical Analysis, Mathematical Programming, Low-rank Matrix +13

First-order methods almost always avoid strict saddle points

Jason D. Lee, Ioannis Panageas, Georgios Piliouras et al. · Mathematical Programming · 2019 · 140 citations

Numerical Analysis, Engineering, Pde-constrained Optimization +4

Gradient Descent Converges to Minimizers

Jason D. Lee, Max Simchowitz, Michael I. Jordan et al. · arXiv (Cornell University) · 2016 · 123 citations · Full text

Engineering, Machine Learning, Random Initialization +13