stochastic gradient descent

An Improved Privacy and Utility Analysis of Differentially Private SGD with Bounded Domain and Smooth Losses AAAI 2026 A Stylometric and Statistical Pipeline for Urdu AI-Generated Text Classification EACL 2026 Asymptotics of Stochastic Gradient Descent with Dropout Regularization in Linear Models JMLR 2026 Can SGD Select Good Fishermen? Local Convergence under Self-Selection Biases (Extended Abstract) COLT 2026 Cheap Bootstrap for Fast Uncertainty Quantification of Stochastic Gradient Descent JMLR 2026 Classical and Quantum Speedups for Non-Convex Optimization via Energy Conserving Descent UAI 2026 Differentiable Filtering for Learning Hidden Markov Models L4DC 2026 Dynamic Momentum Recalibration in Online Gradient Learning CVPR 2026 Enhancing DPSGD via Per-Sample Momentum and Low-Pass Filtering AAAI 2026 Fairness Uncertainty Quantification: A Constrained Stochastic Optimization Perspective UAI 2026 From Continual Learning to SGD and Back: Better Rates for Continual Linear Models ALT 2026 How Learning Dynamics Drive Adversarially Robust Generalization? UAI 2026 Last-Iterate Convergence of Randomized Kaczmarz and SGD with Greedy Step Size COLT 2026 Limitations of SGD for Multi-Index Models Beyond Statistical Queries COLT 2026 Markovian Compression: Looking to the Past Helps Accelerate the Future UAI 2026 Nearly Linear-Time User-Level DP-SCO with Optimal Rates COLT 2026 On-Average Stability of Multipass Preconditioned SGD and Effective Dimension COLT 2026 On the implicit regularization of Langevin dynamics with projected noise COLT 2026 On the Learning Dynamics of Two-layer Linear Networks with Label Noise SGD AAAI 2026 On the Stability of Nonlinear Dynamics in GD and SGD: Beyond Quadratic Potentials COLT 2026 Optimal Learning Rate Schedules under Functional Scaling Laws: Power Decay and Warmup–Stable–Decay (Extended Abstract) COLT 2026 Quantitative Convergence Analysis of Projected Stochastic Gradient Descent for Non-Convex Losses via the Goldstein Subdifferential ALT 2026 Random Reshuffling Dominates Stochastic Gradient Descent COLT 2026 Risk Comparisons in Linear Regression: Implicit Regularization Dominates Explicit Regularization (Extended Abstract) COLT 2026 S-D-RSM: Stochastic Distributed Regularized Splitting Method for Large-Scale Convex Optimization Problems AAAI 2026