gradient clipping

Adam-family Methods for Nonsmooth Optimization with Convergence Guarantees JMLR 2024 An improved analysis of per-sample and per-update clipping in federated learning ICLR 2024 Breaking the Heavy-Tailed Noise Barrier in Stochastic Optimization Problems AISTATS 2024 Byzantine Robustness and Partial Participation Can Be Achieved at Once: Just Clip Gradient Differences NeurIPS 2024 Delving into Differentially Private Transformer ICML 2024 Differentially Private SGD Without Clipping Bias: An Error-Feedback Approach ICLR 2024 Differentially Private Video Activity Recognition WACV 2024 DP-SGD Without Clipping: The Lipschitz Neural Network Way ICLR 2024 Efficiently Train ASR Models that Memorize Less and Perform Better with Per-core Clipping Interspeech 2024 Enhancing High-Resolution 3D Generation through Pixel-wise Gradient Clipping ICLR 2024 High-Probability Bound for Non-Smooth Non-Convex Stochastic Optimization with Heavy Tails ICML 2024 Near-Optimal Streaming Heavy-Tailed Statistical Estimation with Clipped SGD NeurIPS 2024 Online Sensitivity Optimization in Differentially Private Learning AAAI 2024 Parameter-free Clipped Gradient Descent Meets Polyak NeurIPS 2024 Quantifying Unintended Memorization in BEST-RQ ASR Encoders Interspeech 2024 The importance of feature preprocessing for differentially private linear optimization ICLR 2024 A Unified Fast Gradient Clipping Framework for DP-SGD NeurIPS 2023 Automatic Clipping: Differentially Private Deep Learning Made Easier and Stronger NeurIPS 2023 Differentially Private Learning with Per-Sample Adaptive Clipping AAAI 2023 Differentially Private Optimization on Large Model at Small Cost ICML 2023 Differentially Private Sharpness-Aware Training ICML 2023 Disparate Impact in Differential Privacy from Gradient Misalignment ICLR 2023 Effectively Using Public Data in Privacy Preserving Machine Learning ICML 2023 EPISODE: Episodic Gradient Clipping with Periodic Resampled Corrections for Federated Learning with Heterogeneous Data ICLR 2023 Exploring the Limits of Differentially Private Deep Learning with Group-wise Clipping ICLR 2023