hessian approximation

Enhance Curvature Information by Structured Stochastic Quasi-Newton Methods CVPR 2021 Generalization of Quasi-Newton Methods: Application to Robust Symmetric Multisecant Updates AISTATS 2021 Revisiting Weight Initialization of Deep Neural Networks ACML 2021 A Class of Parallel Doubly Stochastic Algorithms for Large-Scale Learning JMLR 2020 Continual Learning With Extended Kronecker-Factored Approximate Curvature CVPR 2020 Do Subsampled Newton Methods Work for High-Dimensional Data? AAAI 2020 Modular Block-diagonal Curvature Approximations for Feedforward Architectures AISTATS 2020 Nesterov's Acceleration for Approximate Newton JMLR 2020 New Insights and Perspectives on the Natural Gradient Method JMLR 2020 SPAN: A Stochastic Projected Approximate Newton Method AAAI 2020 WoodFisher: Efficient Second-Order Approximation for Neural Network Compression NeurIPS 2020 EA-CG: An Approximate Second-Order Method for Training Fully-Connected Neural Networks AAAI 2019 Efficient Learning of Restricted Boltzmann Machines Using Covariance Estimates ACML 2019 Quasi-Newton Trust Region Policy Optimization CoRL 2019 Small Steps and Giant Leaps: Minimal Newton Solvers for Deep Learning ICCV 2019 Inexact trust-region algorithms on Riemannian manifolds NeurIPS 2018 Large Scale Empirical Risk Minimization via Truncated Adaptive Newton Method AISTATS 2018 Asynchronous Stochastic Gradient Descent with Delay Compensation ICML 2017 Sub-sampled Cubic Regularization for Non-convex Optimization ICML 2017 Fast large-scale optimization by unifying stochastic gradient and quasi-Newton methods ICML 2014 Newton Greedy Pursuit: A Quadratic Approximation Method for Sparsity-Constrained Optimization CVPR 2014 Fast Probabilistic Optimization from Noisy Gradients ICML 2013 Quasi-Newton Methods for Markov Chain Monte Carlo NeurIPS 2011 Periodic Step Size Adaptation for Single Pass On-line Learning NeurIPS 2009