stochastic gradient descent

Imitating Deep Learning Dynamics via Locally Elastic Stochastic Differential Equations NeurIPS 2021 Implicit Bias of SGD for Diagonal Linear Networks: a Provable Benefit of Stochasticity NeurIPS 2021 Improved Penalty Method via Doubly Stochastic Gradients for Bilevel Hyperparameter Optimization AAAI 2021 Information-Theoretic Generalization Bounds for Stochastic Gradient Descent COLT 2021 Is SGD a Bayesian sampler? Well, almost JMLR 2021 Label Noise SGD Provably Prefers Flat Global Minimizers NeurIPS 2021 Large-Scale Wasserstein Gradient Flows NeurIPS 2021 Last iterate convergence of SGD for Least-Squares in the Interpolation regime. NeurIPS 2021 Learning from Censored and Dependent Data: The case of Linear Dynamics COLT 2021 Local SGD: Unified Theory and New Efficient Methods AISTATS 2021 Local Stochastic Gradient Descent Ascent: Convergence Analysis and Communication Efficiency AISTATS 2021 Loss Surface Simplexes for Mode Connecting Volumes and Fast Ensembling ICML 2021 L-SVRG and L-Katyusha with Arbitrary Sampling JMLR 2021 Machine Unlearning via Algorithmic Stability COLT 2021 Manipulating SGD with Data Ordering Attacks NeurIPS 2021 Moshpit SGD: Communication-Efficient Decentralized Training on Heterogeneous Unreliable Devices NeurIPS 2021 Multi-Level Local SGD: Distributed SGD for Heterogeneous Hierarchical Networks ICLR 2021 Multilevel Monte Carlo Variational Inference JMLR 2021 (Nearly) Dimension Independent Private ERM with AdaGrad Rates\{via Publicly Estimated Subspaces COLT 2021 Near-optimal Offline and Streaming Algorithms for Learning Non-Linear Dynamical Systems NeurIPS 2021 Neural Mechanics: Symmetry and Broken Conservation Laws in Deep Learning Dynamics ICLR 2021 Neural networks with late-phase weights ICLR 2021 Noise against noise: stochastic label noise helps combat inherent label noise ICLR 2021 Noise and Fluctuation of Finite Learning Rate Stochastic Gradient Descent ICML 2021 Non-Euclidean Differentially Private Stochastic Convex Optimization COLT 2021