learning rate

Fast Mixing of Stochastic Gradient Descent with Normalization and Weight Decay NeurIPS 2022 Improved Classification Rates for Localized SVMs JMLR 2022 Large Learning Rate Tames Homogeneity: Convergence and Balancing Effect ICLR 2022 Learning Rates as a Function of Batch Size: A Random Matrix Theory Approach to Neural Network Training JMLR 2022 Memory Augmented Optimizers for Deep Learning ICLR 2022 Modality-specific Learning Rates for Effective Multimodal Additive Late-fusion ACL 2022 Multiclass Learnability Beyond the PAC Framework: Universal Rates and Partial Concept Classes NeurIPS 2022 No-regret learning in games with noisy feedback: Faster rates and adaptivity via learning rate separation NeurIPS 2022 Nuances in Margin Conditions Determine Gains in Active Learning AISTATS 2022 Nystrom Regularization for Time Series Forecasting JMLR 2022 On Non-local Convergence Analysis of Deep Linear Networks ICML 2022 On the Benefits of Large Learning Rates for Kernel Methods COLT 2022 Optimal Rates for Regularized Conditional Mean Embedding Learning NeurIPS 2022 Scalable One-Pass Optimisation of High-Dimensional Weight-Update Hyperparameters by Implicit Differentiation ICLR 2022 Sharp Analysis of Random Fourier Features in Classification AAAI 2022 Sobolev Norm Learning Rates for Conditional Mean Embeddings AISTATS 2022 Statistical Rates of Convergence for Functional Partially Linear Support Vector Machines for Classification JMLR 2022 Strength of Minibatch Noise in SGD ICLR 2022 Surprising Instabilities in Training Deep Networks and a Theoretical Analysis NeurIPS 2022 Three-stage Evolution and Fast Equilibrium for SGD with Non-degerate Critical Points ICML 2022 Towards Noise-adaptive, Problem-adaptive (Accelerated) Stochastic Gradient Descent ICML 2022 Universal Rates for Interactive Learning NeurIPS 2022 A Diffusion Theory For Deep Learning Dynamics: Stochastic Gradient Descent Exponentially Favors Flat Minima ICLR 2021 An Inertial Newton Algorithm for Deep Learning JMLR 2021 A Unified Convergence Analysis for Shuffling-Type Gradient Methods JMLR 2021