SOTAVerified

Second-order methods

Use second-order statistics to process data.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 51–75 of 181 papers

TitleStatusHype
FLeNS: Federated Learning with Enhanced Nesterov-Newton SketchCode0
Learning Rates as a Function of Batch Size: A Random Matrix Theory Approach to Neural Network TrainingCode0
Adapting Newton's Method to Neural Networks through a Summary of Higher-Order DerivativesCode0
Improving SGD convergence by online linear regression of gradients in multiple statistically relevant directionsCode0
Tensor Normal Training for Deep Learning ModelsCode0
A Mini-Block Fisher Method for Deep Neural Networks—0
Don't Be So Positive: Negative Step Sizes in Second-Order Methods—0
Distributed Second Order Methods with Fast Rates and Compressed Communication—0
Alternating direction method of multipliers for regularized multiclass support vector machines—0
Distributed Quasi-Newton Method for Fair and Fast Federated Learning—0
Doubly Adaptive Scaled Algorithm for Machine Learning Using Second-Order Information—0
A Homogenization Approach for Gradient-Dominated Stochastic Optimization—0
DDPNOpt: Differential Dynamic Programming Neural Optimizer—0
Gram-Gauss-Newton Method: Learning Overparameterized Neural Networks for Regression Problems—0
Adaptive and Optimal Second-order Optimistic Methods for Minimax Optimization—0
Accelerating Stochastic Probabilistic Inference—0
Decentralized Riemannian Conjugate Gradient Method on the Stiefel Manifold—0
Debiasing Distributed Second Order Optimization with Surrogate Sketching and Scaled Regularization—0
Curvature-corrected learning dynamics in deep neural networks—0
A Generic Approach for Escaping Saddle points—0
Critical Point-Finding Methods Reveal Gradient-Flat Regions of Deep Network Losses—0
Convolutions and More as Einsum: A Tensor Network Perspective with Advances for Second-Order Methods—0
A Flexible Tensor Block Coordinate Ascent Scheme for Hypergraph Matching—0
Component-Wise Natural Gradient Descent -- An Efficient Neural Network Optimization—0
Adversarial Vulnerability as a Consequence of On-Manifold Inseparibility—0
Show:102550
← PrevPage 3 of 8Next →

No leaderboard results yet.