stochastic gradient descent

Generalization Bounds using Lower Tail Exponents in Stochastic Optimizers ICML 2022 Global Convergence and Stability of Stochastic Gradient Descent NeurIPS 2022 GraB: Finding Provably Better Data Permutations than Random Reshuffling NeurIPS 2022 Heavy-tailed Streaming Statistical Estimation AISTATS 2022 Hidden Progress in Deep Learning: SGD Learns Parities Near the Computational Limit NeurIPS 2022 Hierarchical Lattice Layer for Partially Monotone Neural Networks NeurIPS 2022 High-dimensional limit theorems for SGD: Effective dynamics and critical scaling NeurIPS 2022 High Probability Generalization Bounds with Fast Rates for Minimax Problems ICLR 2022 High Probability Guarantees for Nonconvex Stochastic Gradient Descent with Heavy Tails ICML 2022 IGLU: Efficient GCN Training via Lazy Updates ICLR 2022 Implicit Gradient Alignment in Distributed and Federated Learning AAAI 2022 Implicit Regularization or Implicit Conditioning? Exact Risk Trajectories of SGD in High Dimensions NeurIPS 2022 Improved Differential Privacy for SGD via Optimal Private Linear Operators on Adaptive Streams NeurIPS 2022 IntSGD: Adaptive Floatless Compression of Stochastic Gradients ICLR 2022 Is Integer Arithmetic Enough for Deep Learning Training? NeurIPS 2022 Label noise (stochastic) gradient descent implicitly solves the Lasso for quadratic parametrisation COLT 2022 Large-Scale Differentially Private BERT EMNLP 2022 Last Iterate Risk Bounds of SGD with Decaying Stepsize for Overparameterized Linear Regression ICML 2022 Learning-based Moving Horizon Estimation through Differentiable Convex Optimization Layers L4DC 2022 Learning Curves for SGD on Structured Features ICLR 2022 Learning Mixture of Neural Temporal Point Processes for Multi-dimensional Event Sequence Clustering IJCAI 2022 Learning with Interactive Models over Decision-Dependent Distributions ACML 2022 Low-Pass Filtering SGD for Recovering Flat Optima in the Deep Learning Optimization Landscape AISTATS 2022 Make Sharpness-Aware Minimization Stronger: A Sparsified Perturbation Approach NeurIPS 2022 Making SGD Parameter-Free COLT 2022