SOTAVerified

Second-order methods

Use second-order statistics to process data.

Papers

Showing 150 of 181 papers

TitleStatusHype
Automatic Gradient Descent: Deep Learning without HyperparametersCode2
Differentiable Expected Hypervolume Improvement for Parallel Multi-Objective Bayesian OptimizationCode2
Towards Practical Second-Order Optimizers in Deep Learning: Insights from Fisher Information AnalysisCode2
MKOR: Momentum-Enabled Kronecker-Factor-Based Optimizer Using Rank-1 UpdatesCode1
Second-Order Neural ODE OptimizerCode1
ADAHESSIAN: An Adaptive Second Order Optimizer for Machine LearningCode1
Structured Inverse-Free Natural Gradient: Memory-Efficient & Numerically-Stable KFACCode1
Low Rank Saddle Free Newton: A Scalable Method for Stochastic Nonconvex OptimizationCode1
M-FAC: Efficient Matrix-Free Approximations of Second-Order InformationCode1
Revisiting Scalable Hessian Diagonal Approximations for Applications in Reinforcement LearningCode1
Can We Remove the Square-Root in Adaptive Gradient Methods? A Second-Order PerspectiveCode1
Second-Order Stochastic Optimization for Machine Learning in Linear TimeCode1
MiLeNAS: Efficient Neural Architecture Search via Mixed-Level ReformulationCode1
Symmetry Teleportation for Accelerated OptimizationCode1
SASSHA: Sharpness-aware Adaptive Second-order Optimization with Stable Hessian ApproximationCode1
Communication-Efficient Stochastic Zeroth-Order Optimization for Federated LearningCode1
Near out-of-distribution detection for low-resolution radar micro-Doppler signaturesCode1
Adaptive Consensus Optimization Method for GANsCode0
Sharpened Lazy Incremental Quasi-Newton MethodCode0
Stochastic Trust Region Inexact Newton Method for Large-scale Machine LearningCode0
SGD momentum optimizer with step estimation by online parabola modelCode0
Studying K-FAC Heuristics by Viewing Adam through a Second-Order LensCode0
SGD with Partial Hessian for Deep Neural Networks OptimizationCode0
Tensor Normal Training for Deep Learning ModelsCode0
A Gauss-Newton Approach for Min-Max Optimization in Generative Adversarial NetworksCode0
Adapting Newton's Method to Neural Networks through a Summary of Higher-Order DerivativesCode0
NysAct: A Scalable Preconditioned Gradient Descent using Nystrom ApproximationCode0
Stochastic Newton and Cubic Newton Methods with Simple Local Linear-Quadratic RatesCode0
Newtonian Monte Carlo: single-site MCMC meets second-order gradient methodsCode0
Stochastic Variance-Reduced Newton: Accelerating Finite-Sum Minimization with Large BatchesCode0
Online Covariance Matrix Estimation in Sketched Newton MethodsCode0
A Computationally Efficient Sparsified Online Newton MethodCode0
Statistical Inference of Constrained Stochastic Optimization via Sketched Sequential Quadratic ProgrammingCode0
AdaSub: Stochastic Optimization Using Second-Order Information in Low-Dimensional SubspacesCode0
On the Promise of the Stochastic Generalized Gauss-Newton Method for Training DNNsCode0
Improving SGD convergence by online linear regression of gradients in multiple statistically relevant directionsCode0
Generalized Optimistic Methods for Convex-Concave Saddle Point ProblemsCode0
ISAAC Newton: Input-based Approximate Curvature for Newton's MethodCode0
FLeNS: Federated Learning with Enhanced Nesterov-Newton SketchCode0
Fast and Furious Convergence: Stochastic Second Order Methods under InterpolationCode0
FOSI: Hybrid First and Second Order OptimizationCode0
Large batch size training of neural networks with adversarial training and second-order informationCode0
Differentially Private Image Classification from FeaturesCode0
Error Feedback Can Accurately Compress PreconditionersCode0
Nonlinear matrix recovery using optimization on the Grassmann manifoldCode0
Alternating Iteratively Reweighted _1 and Subspace Newton Algorithms for Nonconvex Sparse OptimizationCode0
LIBS2ML: A Library for Scalable Second Order Machine Learning AlgorithmsCode0
Exact, Tractable Gauss-Newton Optimization in Deep Reversible Architectures Reveal Poor GeneralizationCode0
Limitations of the Empirical Fisher Approximation for Natural Gradient DescentCode0
Optimization Methods for Supervised Machine Learning: From Linear Models to Deep LearningCode0
Show:102550
← PrevPage 1 of 4Next →

No leaderboard results yet.