stochastic gradient descent

Exploring the Inefficiency of Heavy Ball as Momentum Parameter Approaches 1 IJCAI 2024 Fast Equilibrium of SGD in Generic Situations ICLR 2024 Fast Forwarding Low-Rank Training EMNLP 2024 Fast Stealthily Biased Sampling Using Sliced Wasserstein Distance ACML 2024 Feature Contamination: Neural Networks Learn Uncorrelated Features and Fail to Generalize ICML 2024 Federated Learning under Periodic Client Participation and Heterogeneous Data: A New Communication-Efficient Algorithm and Analysis NeurIPS 2024 Fine-grained Analysis of Stability and Generalization for Stochastic Bilevel Optimization IJCAI 2024 Freya PAGE: First Optimal Time Complexity for Large-Scale Nonconvex Finite-Sum Optimization with Heterogeneous Asynchronous Computations NeurIPS 2024 Generalization Bounds for Label Noise Stochastic Gradient Descent AISTATS 2024 General Stability Analysis for Zeroth-Order Optimization Algorithms ICLR 2024 GGD: Grafting Gradient Descent JMLR 2024 High-dimensional SGD aligns with emerging outlier eigenspaces ICLR 2024 High Probability Convergence Bounds for Non-convex Stochastic Gradient Descent with Sub-Weibull Noise JMLR 2024 Hop, skip, jump to Convergence: Dynamics of Learning Rate Transitions for Improved Training of Large Language Models EMNLP 2024 How to Fine-Tune Vision Models with SGD ICLR 2024 Implicit Bias in Noisy-SGD: With Applications to Differentially Private Training AISTATS 2024 Implicit bias of SGD in L_2-regularized linear DNNs: One-way jumps from high to low rank ICLR 2024 Improved Sample Complexity Analysis of Natural Policy Gradient Algorithm with General Parameterization for Infinite Horizon Discounted Reward Markov Decision Processes AISTATS 2024 In Search of a Data Transformation That Accelerates Neural Field Training CVPR 2024 Iterate Averaging in the Quest for Best Test Error JMLR 2024 Ito Diffusion Approximation of Universal Ito Chains for Sampling, Optimization and Boosting ICLR 2024 LabelDP-Pro: Learning with Label Differential Privacy via Projections ICLR 2024 Large Stepsize Gradient Descent for Logistic Loss: Non-Monotonicity of the Loss Improves Optimization Efficiency COLT 2024 Law of Large Numbers and Central Limit Theorem for Wide Two-layer Neural Networks: The Mini-Batch and Noisy Case JMLR 2024 Learn To Unlearn for Deep Neural Networks: Minimizing Unlearning Interference With Gradient Projection WACV 2024