stochastic gradient descent

Toward Large Kernel Models ICML 2023 Towards Sustainable Learning: Coresets for Data-efficient Deep Learning ICML 2023 Trainable Weight Averaging: Efficient Training by Optimizing Historical Solutions ICLR 2023 Two Losses Are Better Than One: Faster Optimization Using a Cheaper Proxy ICML 2023 Two Sides of One Coin: the Limits of Untuned SGD and the Power of Adaptive Methods NeurIPS 2023 Understanding the Generalization Ability of Deep Learning Algorithms: A Kernelized Rényi's Entropy Perspective IJCAI 2023 Unified Enhancement of Privacy Bounds for Mixture Mechanisms via f-Differential Privacy NeurIPS 2023 Uniform-in-Time Wasserstein Stability Bounds for (Noisy) Stochastic Gradient Descent NeurIPS 2023 User-level Private Stochastic Convex Optimization with Optimal Rates ICML 2023 Variational Sparse Inverse Cholesky Approximation for Latent Gaussian Processes via Double Kullback-Leibler Minimization ICML 2023 Why Does Sharpness-Aware Minimization Generalize Better Than SGD? NeurIPS 2023 Winner-Take-All Column Row Sampling for Memory Efficient Adaptation of Language Model NeurIPS 2023 Accelerated SGD for Non-Strongly-Convex Least Squares COLT 2022 Accelerating SGD for Highly Ill-Conditioned Huge-Scale Online Matrix Completion NeurIPS 2022 Accelerating training of batch normalization: A manifold perspective UAI 2022 A Communication-Efficient Distributed Gradient Clipping Algorithm for Training Deep Neural Networks NeurIPS 2022 Active Labeling: Streaming Stochastic Gradients NeurIPS 2022 AdaBlock: SGD with Practical Block Diagonal Matrix Adaptation for Deep Learning AISTATS 2022 Adam Can Converge Without Any Modification On Update Rules NeurIPS 2022 Adaptation of the Independent Metropolis-Hastings Sampler with Normalizing Flow Proposals AISTATS 2022 Adaptive Inertia: Disentangling the Effects of Adaptive Learning Rate and Momentum ICML 2022 A General Analysis of Example-Selection for Stochastic Gradient Descent ICLR 2022 A general sample complexity analysis of vanilla policy gradient AISTATS 2022 A Momentumized, Adaptive, Dual Averaged Gradient Method JMLR 2022 Anytime Guarantees under Heavy-Tailed Data AAAI 2022