SOTAVerified

Second-order methods

Use second-order statistics to process data.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 26–50 of 181 papers

TitleStatusHype
Adapting Newton's Method to Neural Networks through a Summary of Higher-Order DerivativesCode0
Newtonian Monte Carlo: single-site MCMC meets second-order gradient methodsCode0
SGD momentum optimizer with step estimation by online parabola modelCode0
Adaptive Consensus Optimization Method for GANsCode0
Sharpened Lazy Incremental Quasi-Newton MethodCode0
Nonlinear matrix recovery using optimization on the Grassmann manifoldCode0
LocoProp: Enhancing BackProp via Local Loss OptimizationCode0
Statistical Inference of Constrained Stochastic Optimization via Sketched Sequential Quadratic ProgrammingCode0
AdaSub: Stochastic Optimization Using Second-Order Information in Low-Dimensional SubspacesCode0
NysAct: A Scalable Preconditioned Gradient Descent using Nystrom ApproximationCode0
Generalized Optimistic Methods for Convex-Concave Saddle Point ProblemsCode0
FOSI: Hybrid First and Second Order OptimizationCode0
Improving SGD convergence by online linear regression of gradients in multiple statistically relevant directionsCode0
Fast and Furious Convergence: Stochastic Second Order Methods under InterpolationCode0
Exact, Tractable Gauss-Newton Optimization in Deep Reversible Architectures Reveal Poor GeneralizationCode0
A Computationally Efficient Sparsified Online Newton MethodCode0
Limitations of the Empirical Fisher Approximation for Natural Gradient DescentCode0
FLeNS: Federated Learning with Enhanced Nesterov-Newton SketchCode0
ISAAC Newton: Input-based Approximate Curvature for Newton's MethodCode0
Differentially Private Image Classification from FeaturesCode0
Alternating Iteratively Reweighted _1 and Subspace Newton Algorithms for Nonconvex Sparse OptimizationCode0
LIBS2ML: A Library for Scalable Second Order Machine Learning AlgorithmsCode0
Learning Rates as a Function of Batch Size: A Random Matrix Theory Approach to Neural Network TrainingCode0
On the Promise of the Stochastic Generalized Gauss-Newton Method for Training DNNsCode0
Error Feedback Can Accurately Compress PreconditionersCode0
Show:102550
← PrevPage 2 of 8Next →

No leaderboard results yet.