learning rate

Finite-Time Performance Bounds and Adaptive Learning Rate Selection for Two Time-Scale Reinforcement Learning NeurIPS 2019 Interaction Matters: A Note on Non-asymptotic Local Convergence of Generative Adversarial Networks AISTATS 2019 Learning rates for Gaussian mixtures under group action COLT 2019 Lipschitz Adaptivity with Multiple Learning Rates in Online Learning COLT 2019 Localized Structured Prediction NeurIPS 2019 On the optimality of the Hedge algorithm in the stochastic regime JMLR 2019 On the Relation Between the Sharpest Directions of DNN Loss and the SGD Step Length ICLR 2019 Sharp Analysis of Learning with Discrete Losses AISTATS 2019 The Effect of Network Width on Stochastic Gradient Descent and Generalization: an Empirical Study ICML 2019 Theoretical Analysis of Auto Rate-Tuning by Batch Normalization ICLR 2019 Towards Explaining the Regularization Effect of Initial Large Learning Rate in Training Neural Networks NeurIPS 2019 Understanding the Impact of Entropy on Policy Optimization ICML 2019 Understanding the Role of Momentum in Stochastic Gradient Methods NeurIPS 2019 Universal Statistics of Fisher Information in Deep Neural Networks: Mean Field Approach AISTATS 2019 Using Statistics to Automate Stochastic Optimization NeurIPS 2019 When can unlabeled data improve the learning rate? COLT 2019 A Bayesian Perspective on Generalization and Stochastic Gradient Descent ICLR 2018 Adaptive Methods for Nonconvex Optimization NeurIPS 2018 A Probabilistic Theory of Supervised Similarity Learning for Pointwise ROC Curve Optimization ICML 2018 But How Does It Work in Theory? Linear SVM with Random Features NeurIPS 2018 Demystifying excessively volatile human learning: A Bayesian persistent prior and a neural approximation NeurIPS 2018 Don't Decay the Learning Rate, Increase the Batch Size ICLR 2018 How SGD Selects the Global Minima in Over-parameterized Learning: A Dynamical Stability Perspective NeurIPS 2018 L4: Practical loss-based stepsize adaptation for deep learning NeurIPS 2018 SGD and Hogwild! Convergence Without the Bounded Gradients Assumption ICML 2018