stochastic gradient descent

Markov Chain Score Ascent: A Unifying Framework of Variational Inference with Markovian Gradients NeurIPS 2022 Masked Training of Neural Networks with Partial Gradients AISTATS 2022 Mean-field Analysis of Piecewise Linear Solutions for Wide ReLU Networks JMLR 2022 Minibatch vs Local SGD with Shuffling: Tight Convergence Bounds and Beyond ICLR 2022 Momentum Aggregation for Private Non-convex ERM NeurIPS 2022 Multi-agent Performative Prediction with Greedy Deployment and Consensus Seeking Agents NeurIPS 2022 Multirate Training of Neural Networks ICML 2022 (Nearly) Optimal Private Linear Regression for Sub-Gaussian Data via Adaptive Clipping COLT 2022 Neural Network Weights Do Not Converge to Stationary Points: An Invariant Measure Perspective ICML 2022 Non-Vacuous Generalisation Bounds for Shallow Neural Networks ICML 2022 Offline Neural Contextual Bandits: Pessimism, Optimization and Generalization ICLR 2022 On Almost Sure Convergence Rates of Stochastic Gradient Methods COLT 2022 On Biased Stochastic Gradient Estimation JMLR 2022 One size does not fit all: Investigating strategies for differentially-private learning across NLP tasks EMNLP 2022 Online Nonsubmodular Minimization with Delayed Costs: From Full Information to Bandit Feedback ICML 2022 On the Convergence of mSGD and AdaGrad for Stochastic Optimization ICLR 2022 On the Double Descent of Random Features Models Trained with SGD NeurIPS 2022 On the generalization of learning algorithms that do not converge NeurIPS 2022 On the Generalization of Models Trained with SGD: Information-Theoretic Bounds and Implications ICLR 2022 On the Last Iterate Convergence of Momentum Methods ALT 2022 On the non-universality of deep learning: quantifying the cost of symmetry NeurIPS 2022 On the Theoretical Properties of Noise Correlation in Stochastic Optimization NeurIPS 2022 Optimization and Adaptive Generalization of Three layer Neural Networks ICLR 2022 Permutation-Based SGD: Is Random Optimal? ICLR 2022 Phase diagram of Stochastic Gradient Descent in high-dimensional two-layer neural networks NeurIPS 2022