conftrace_

second-order method

38 papers

Explore in graph

Co-occurring keywords

second-order optimization (93) stochastic optimization (1060) newton method (64) hessian approximation (41) convex optimization (1321) neural network optimization (1293) stochastic gradient descent (1091) first-order method (89) regret bound (1926) linear convergence (158)

Papers

Second-order Information Promotes Mini-Batch Robustness in Variance-Reduced Gradients JMLR 2025
Adaptive and Optimal Second-order Optimistic Methods for Minimax Optimization NIPS 2024
Exploring Jacobian Inexactness in Second-Order Methods for Variational Inequalities: Lower Bounds, Optimal Algorithms and Quasi-Newton Approximations NIPS 2024
Second Order Methods for Bandit Optimization and Control COLT 2024
A projected semismooth Newton method for a class of nonconvex composite programs with strong prox-regularity JMLR 2024
Stochastic Newton Proximal Extragradient Method NIPS 2024
A Second-Order Method for Stochastic Bandit Convex Optimisation COLT 2023
STay-ON-the-Ridge: Guaranteed Convergence to Local Minimax Equilibrium in Nonconvex-Nonconcave Games COLT 2023
MKOR: Momentum-Enabled Kronecker-Factor-Based Optimizer Using Rank-1 Updates NIPS 2023
A Mini-Block Fisher Method for Deep Neural Networks AISTATS 2023
Block Low-Rank Preconditioner with Shared Basis for Stochastic Optimization NIPS 2023
Faster Differentially Private Convex Optimization via Second-Order Methods NIPS 2023
Optimal and Adaptive Monteiro-Svaiter Acceleration NIPS 2022
LocoProp: Enhancing BackProp via Local Loss Optimization AISTATS 2022
Stochastic Second-Order Methods Improve Best-Known Sample Complexity of SGD for Gradient-Dominated Functions NIPS 2022
FedNL: Making Newton-Type Methods Applicable to Federated Learning ICML 2022
Tensor Normal Training for Deep Learning Models NIPS 2021
GO Hessian for Expectation-Based Objectives AAAI 2021
A Scalable Second Order Method for Ill-Conditioned Matrix Completion from Few Samples ICML 2021
Distributed Second Order Methods with Fast Rates and Compressed Communication ICML 2021
LocalNewton: Reducing communication rounds for distributed learning UAI 2021
Learning from Censored and Dependent Data: The case of Linear Dynamics COLT 2021
Approximate Newton Methods JMLR 2021
Convex optimization based on global lower second-order models NIPS 2020
Second-Order Information in Non-Convex Stochastic Optimization: Power and Limitations COLT 2020