SOTAVerified

Second-order methods

Use second-order statistics to process data.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 151–175 of 181 papers

TitleStatusHype
SGD momentum optimizer with step estimation by online parabola modelCode0
SGD with Partial Hessian for Deep Neural Networks OptimizationCode0
FLeNS: Federated Learning with Enhanced Nesterov-Newton SketchCode0
FOSI: Hybrid First and Second Order OptimizationCode0
Generalized Optimistic Methods for Convex-Concave Saddle Point ProblemsCode0
Newtonian Monte Carlo: single-site MCMC meets second-order gradient methodsCode0
Sharpened Lazy Incremental Quasi-Newton MethodCode0
Asymptotic Analysis of Conditioned Stochastic Gradient DescentCode0
Alternating Iteratively Reweighted _1 and Subspace Newton Algorithms for Nonconvex Sparse OptimizationCode0
Nonlinear matrix recovery using optimization on the Grassmann manifoldCode0
NysAct: A Scalable Preconditioned Gradient Descent using Nystrom ApproximationCode0
Studying K-FAC Heuristics by Viewing Adam through a Second-Order LensCode0
Improving SGD convergence by online linear regression of gradients in multiple statistically relevant directionsCode0
Online Covariance Matrix Estimation in Sketched Newton MethodsCode0
A Gauss-Newton Approach for Min-Max Optimization in Generative Adversarial NetworksCode0
ISAAC Newton: Input-based Approximate Curvature for Newton's MethodCode0
Tensor Normal Training for Deep Learning ModelsCode0
Stochastic Trust Region Inexact Newton Method for Large-scale Machine LearningCode0
On the Promise of the Stochastic Generalized Gauss-Newton Method for Training DNNsCode0
Stochastic Variance-Reduced Newton: Accelerating Finite-Sum Minimization with Large BatchesCode0
Optimization Methods for Supervised Machine Learning: From Linear Models to Deep LearningCode0
Large batch size training of neural networks with adversarial training and second-order informationCode0
Adapting Newton's Method to Neural Networks through a Summary of Higher-Order DerivativesCode0
Stochastic Newton and Cubic Newton Methods with Simple Local Linear-Quadratic RatesCode0
Limitations of the Empirical Fisher Approximation for Natural Gradient DescentCode0
Show:102550
← PrevPage 7 of 8Next →

No leaderboard results yet.