second-order method

Cubic regularized subspace Newton for non-convex optimization AISTATS 2025 Improving Stochastic Cubic Newton with Momentum AISTATS 2025 Second-order Information Promotes Mini-Batch Robustness in Variance-Reduced Gradients JMLR 2025 Second-Order Min-Max Optimization with Lazy Hessians ICLR 2025 Adaptive and Optimal Second-order Optimistic Methods for Minimax Optimization NeurIPS 2024 A Homogenization Approach for Gradient-Dominated Stochastic Optimization UAI 2024 A projected semismooth Newton method for a class of nonconvex composite programs with strong prox-regularity JMLR 2024 Exploring Jacobian Inexactness in Second-Order Methods for Variational Inequalities: Lower Bounds, Optimal Algorithms and Quasi-Newton Approximations NeurIPS 2024 Second Order Methods for Bandit Optimization and Control COLT 2024 Stochastic Newton Proximal Extragradient Method NeurIPS 2024 A Mini-Block Fisher Method for Deep Neural Networks AISTATS 2023 A Second-Order Method for Stochastic Bandit Convex Optimisation COLT 2023 Block Low-Rank Preconditioner with Shared Basis for Stochastic Optimization NeurIPS 2023 Faster Differentially Private Convex Optimization via Second-Order Methods NeurIPS 2023 MKOR: Momentum-Enabled Kronecker-Factor-Based Optimizer Using Rank-1 Updates NeurIPS 2023 SP2 : A Second Order Stochastic Polyak Method ICLR 2023 STay-ON-the-Ridge: Guaranteed Convergence to Local Minimax Equilibrium in Nonconvex-Nonconcave Games COLT 2023 FedNL: Making Newton-Type Methods Applicable to Federated Learning ICML 2022 LocoProp: Enhancing BackProp via Local Loss Optimization AISTATS 2022 Optimal and Adaptive Monteiro-Svaiter Acceleration NeurIPS 2022 Stochastic Second-Order Methods Improve Best-Known Sample Complexity of SGD for Gradient-Dominated Functions NeurIPS 2022 Approximate Newton Methods JMLR 2021 A Scalable Second Order Method for Ill-Conditioned Matrix Completion from Few Samples ICML 2021 Bilinear Parameterization for Non-Separable Singular Value Penalties CVPR 2021 Distributed Second Order Methods with Fast Rates and Compressed Communication ICML 2021