gradient norm

Time-Reversed Dissipation Induces Duality Between Minimizing Gradient Norm and Function Value NeurIPS 2023 Two Sides of One Coin: the Limits of Untuned SGD and the Power of Adaptive Methods NeurIPS 2023 Boosting Active Learning via Improving Test Performance AAAI 2022 On the Importance of Gradient Norm in PAC-Bayesian Bounds NeurIPS 2022 Oracle Complexity in Nonsmooth Nonconvex Optimization JMLR 2022 Penalizing Gradient Norm for Efficiently Improving Generalization in Deep Learning ICML 2022 Practical Schemes for Finding Near-Stationary Points of Convex Finite-Sums AISTATS 2022 Pruning has a disparate impact on model accuracy NeurIPS 2022 Revisit last-iterate convergence of mSGD under milder requirement on step size NeurIPS 2022 Sandwich Batch Normalization: A Drop-In Replacement for Feature Distribution Heterogeneity WACV 2022 Temporal Effective Batch Normalization in Spiking Neural Networks NeurIPS 2022 The Power of Adaptivity in SGD: Self-Tuning Step Sizes with Unbounded Gradients and Affine Variance COLT 2022 Accelerated Algorithms for Smooth Convex-Concave Minimax Problems with O(1/k^2) Rate on Squared Gradient Norm ICML 2021 A Geometric Structure of Acceleration and Its Role in Making Gradients Small Fast NeurIPS 2021 Beyond BatchNorm: Towards a Unified Understanding of Normalization in Deep Learning NeurIPS 2021 Deep Learning on a Data Diet: Finding Important Examples Early in Training NeurIPS 2021 Fast and Memory Efficient Differentially Private-SGD via JL Projections NeurIPS 2021 On the Importance of Gradients for Detecting Distributional Shifts in the Wild NeurIPS 2021 Parameter-free, Dynamic, and Strongly-Adaptive Online Learning ICML 2020 The Complexity of Finding Stationary Points with Stochastic Gradient Descent ICML 2020 DINGO: Distributed Newton-Type Method for Gradient-Norm Optimization NeurIPS 2019 Sorting Out Lipschitz Function Approximation ICML 2019 How To Make the Gradients Small Stochastically: Even Faster Convex and Nonconvex SGD NeurIPS 2018 BING: Binarized Normed Gradients for Objectness Estimation at 300fps CVPR 2014