gradient clipping

An Improved Privacy and Utility Analysis of Differentially Private SGD with Bounded Domain and Smooth Losses AAAI 2026 ASKD: Reinforcement Learning-Style Knowledge Distillation with Quality-Adaptive Skewness AAAI 2026 Byzantine-Robust and Differentially Private Federated Optimization under Weaker Assumptions UAI 2026 High Probability Convergence Guarantees of Stochastic Gradient Descent Ascent in Structured Nonconvex Min-Max Games COLT 2026 Online Convex Optimization with Heavy Tails: Old Algorithms, New Regrets, and Applications ALT 2026 Stochastic Gradient Methods: Bias, Stability and Generalization JMLR 2026 Tight Long-Term Tail Decay of (Clipped) SGD in Non-Convex Optimization COLT 2026 Vanilla SGD with Momentum Survives Heavy-Tailed Noise: Convergence Analysis without Gradient Clipping or Normalization UAI 2026 Clipping Improves Adam-Norm and AdaGrad-Norm when the Noise Is Heavy-Tailed ICML 2025 Convergence of Distributed Adaptive Optimization with Local Updates ICLR 2025 Differential Privacy in Distributed Learning: Beyond Uniformly Bounded Stochastic Gradients AISTATS 2025 Dyn-D^2P: Dynamic Differentially Private Decentralized Learning with Provable Utility Guarantee IJCAI 2025 From Gradient Clipping to Normalization for Heavy Tailed SGD AISTATS 2025 Methods for Convex $(L_0,L_1)$-Smooth Optimization: Clipping, Acceleration, and Adaptivity ICLR 2025 Methods with Local Steps and Random Reshuffling for Generally Smooth Non-Convex Federated Optimization ICLR 2025 Nonconvex Stochastic Optimization under Heavy-Tailed Noises: Optimal Convergence without Gradient Clipping ICLR 2025 Nonlinearly Preconditioned Gradient Methods under Generalized Smoothness ICML 2025 Optimized Gradient Clipping for Noisy Label Learning AAAI 2025 Revisiting Gradient Normalization and Clipping for Nonconvex SGD under Heavy-Tailed Noise: Necessity, Sufficiency, and Acceleration JMLR 2025 Revisiting Large-Scale Non-convex Distributionally Robust Optimization ICLR 2025 Revisit Micro-batch Clipping: Adaptive Data Pruning via Gradient Manipulation ICLR 2025 SPAM: Spike-Aware Adam with Momentum Reset for Stable LLM Training ICLR 2025 The Last Iterate Advantage: Empirical Auditing and Principled Heuristic Analysis of Differentially Private SGD ICLR 2025 To Clip or not to Clip: the Dynamics of SGD with Gradient Clipping in High-Dimensions ICLR 2025 Towards hyperparameter-free optimization with differential privacy ICLR 2025