SOTAVerified

Second-order methods

Use second-order statistics to process data.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–50 of 181 papers

TitleStatusHype
Towards Practical Second-Order Optimizers in Deep Learning: Insights from Fisher Information AnalysisCode2
Automatic Gradient Descent: Deep Learning without HyperparametersCode2
Differentiable Expected Hypervolume Improvement for Parallel Multi-Objective Bayesian OptimizationCode2
Communication-Efficient Stochastic Zeroth-Order Optimization for Federated LearningCode1
Second-Order Neural ODE OptimizerCode1
Second-Order Stochastic Optimization for Machine Learning in Linear TimeCode1
MKOR: Momentum-Enabled Kronecker-Factor-Based Optimizer Using Rank-1 UpdatesCode1
Can We Remove the Square-Root in Adaptive Gradient Methods? A Second-Order PerspectiveCode1
Symmetry Teleportation for Accelerated OptimizationCode1
Near out-of-distribution detection for low-resolution radar micro-Doppler signaturesCode1
M-FAC: Efficient Matrix-Free Approximations of Second-Order InformationCode1
SASSHA: Sharpness-aware Adaptive Second-order Optimization with Stable Hessian ApproximationCode1
ADAHESSIAN: An Adaptive Second Order Optimizer for Machine LearningCode1
Low Rank Saddle Free Newton: A Scalable Method for Stochastic Nonconvex OptimizationCode1
MiLeNAS: Efficient Neural Architecture Search via Mixed-Level ReformulationCode1
Revisiting Scalable Hessian Diagonal Approximations for Applications in Reinforcement LearningCode1
Structured Inverse-Free Natural Gradient: Memory-Efficient & Numerically-Stable KFACCode1
Accelerating Stochastic Probabilistic Inference—0
Adaptive and Optimal Second-order Optimistic Methods for Minimax Optimization—0
Distributed Quasi-Newton Method for Fair and Fast Federated Learning—0
A block coordinate descent optimizer for classification problems exploiting convexity—0
A Flexible Tensor Block Coordinate Ascent Scheme for Hypergraph Matching—0
Adversarial Vulnerability as a Consequence of On-Manifold Inseparibility—0
Accelerating SGD for Distributed Deep-Learning Using Approximated Hessian Matrix—0
DDPNOpt: Differential Dynamic Programming Neural Optimizer—0
A Generic Approach for Escaping Saddle points—0
Gram-Gauss-Newton Method: Learning Overparameterized Neural Networks for Regression Problems—0
A Homogenization Approach for Gradient-Dominated Stochastic Optimization—0
Alternating direction method of multipliers for regularized multiclass support vector machines—0
A Mini-Block Fisher Method for Deep Neural Networks—0
Distributed Second Order Methods with Fast Rates and Compressed Communication—0
A Distributed Second-Order Algorithm You Can Trust—0
Bilinear Parameterization for Non-Separable Singular Value Penalties—0
A Distributed Optimisation Framework Combining Natural Gradient with Hessian-Free for Discriminative Sequence Training—0
A Decentralized Quasi-Newton Method for Dual Formulations of Consensus Optimization—0
Accelerated Training of Federated Learning via Second-Order Methods—0
KOALA++: Efficient Kalman-Based Optimization of Neural Networks with Gradient-Covariance Products—0
Curvature-corrected learning dynamics in deep neural networks—0
Debiasing Distributed Second Order Optimization with Surrogate Sketching and Scaled Regularization—0
A Survey of Optimization Methods for Training DL Models: Theoretical Perspective on Convergence and Generalization—0
Basis Matters: Better Communication-Efficient Second Order Methods for Federated Learning—0
Bilinear Parameterization For Differentiable Rank-Regularization—0
A survey of deep learning optimizers -- first and second order methods—0
Biologically inspired protection of deep networks from adversarial attacks—0
Block-diagonal Hessian-free Optimization for Training Neural Networks—0
Adaptive Single-Pass Stochastic Gradient Descent in Input Sparsity Time—0
A scaled gradient projection method for Bayesian learning in dynamical systems—0
Component-Wise Natural Gradient Descent -- An Efficient Neural Network Optimization—0
Convolutions and More as Einsum: A Tensor Network Perspective with Advances for Second-Order Methods—0
Approximate Newton Methods and Their Local Convergence—0
Show:102550
← PrevPage 1 of 4Next →

No leaderboard results yet.