non-convex optimization

L-SVRG and L-Katyusha with Arbitrary Sampling JMLR 2021 MARINA: Faster Non-Convex Distributed Learning with Compression ICML 2021 Multi-Level Local SGD: Distributed SGD for Heterogeneous Hierarchical Networks ICLR 2021 Multiplicative Noise and Heavy Tails in Stochastic Optimization ICML 2021 Noisy Gradient Descent Converges to Flat Minima for Nonconvex Matrix Factorization AISTATS 2021 Non-convex Distributionally Robust Optimization: Non-asymptotic Analysis NeurIPS 2021 Non-PSD matrix sketching with applications to regression and optimization UAI 2021 NOVAS: Non-convex Optimization via Adaptive Stochastic Search for End-to-end Learning and Control ICLR 2021 On a Combination of Alternating Minimization and Nesterov’s Momentum ICML 2021 Online stochastic gradient descent on non-convex losses from high-dimensional inference JMLR 2021 On the Convergence of Step Decay Step-Size for Stochastic Optimization NeurIPS 2021 On the Second-order Convergence Properties of Random Search Methods NeurIPS 2021 On the Theory of Implicit Deep Learning: Global Convergence with Implicit Layers ICLR 2021 Optimal Complexity in Decentralized Training ICML 2021 Optimal Non-Convex Exact Recovery in Stochastic Block Model via Projected Power Method ICML 2021 Oracle Complexity in Nonsmooth Nonconvex Optimization NeurIPS 2021 PAGE: A Simple and Optimal Probabilistic Gradient Estimator for Nonconvex Optimization ICML 2021 Preconditioned Gradient Descent for Over-Parameterized Nonconvex Matrix Factorization NeurIPS 2021 Private Stochastic Non-convex Optimization with Improved Utility Rates IJCAI 2021 Projected Stochastic Gradient Langevin Algorithms for Constrained Sampling and Non-Convex Learning COLT 2021 Proximal Gradient Descent-Ascent: Variable Convergence under KŁ Geometry ICLR 2021 Proxy Convexity: A Unified Framework for the Analysis of Neural Networks Trained by Gradient Descent NeurIPS 2021 QISTA-Net-Audio: Audio Super-Resolution via Non-Convex ℓ_q-Norm Minimization Interspeech 2021 Rank Overspecified Robust Matrix Recovery: Subgradient Method and Exact Recovery NeurIPS 2021 Rate-improved inexact augmented Lagrangian method for constrained nonconvex optimization AISTATS 2021