optimization theory

Towards Understanding Why Lookahead Generalizes Better Than SGD and Beyond NeurIPS 2021 Can Implicit Bias Explain Generalization? Stochastic Convex Optimization as a Case Study NeurIPS 2020 Explore Aggressively, Update Conservatively: Stochastic Extragradient Methods with Variable Stepsize Scaling NeurIPS 2020 Tight Dimension Independent Lower Bound on the Expected Convergence Rate for Diminishing Step Sizes in SGD NeurIPS 2019 Differential Equations for Modeling Asynchronous Algorithms IJCAI 2018 Spurious Local Minima are Common in Two-Layer ReLU Neural Networks ICML 2018 Understanding Generalization and Optimization Performance of Deep CNNs ICML 2018 Adaptive Relaxed ADMM: Convergence Theory and Practical Implementation CVPR 2017 Failures of Gradient-Based Deep Learning ICML 2017 Sharpness, Restart and Acceleration NeurIPS 2017 Matrix Completion has No Spurious Local Minimum NeurIPS 2016 On the Influence of Momentum Acceleration on Online Learning JMLR 2016 The Power of Optimization from Samples NeurIPS 2016 On the Global Linear Convergence of Frank-Wolfe Optimization Variants NeurIPS 2015 Identifying and attacking the saddle point problem in high-dimensional non-convex optimization NeurIPS 2014 Optimization Equivalence of Divergences Improves Neighbor Embedding ICML 2014 Approximating Semidefinite Programs in Sublinear Time NeurIPS 2011 Convergence Rates of Inexact Proximal-Gradient Methods for Convex Optimization NeurIPS 2011 Lower Bounds on Rate of Convergence of Cutting Plane Methods NeurIPS 2010 On the Convergence of the Concave-Convex Procedure NeurIPS 2009 Comments on the Complete Characterization of a Family of Solutions to a Generalized Fisher Criterion JMLR 2008