SOTAVerified

Second-order methods

Use second-order statistics to process data.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 76–100 of 181 papers

TitleStatusHype
A Novel Fast Exact Subproblem Solver for Stochastic Quasi-Newton Cubic Regularized Optimization—0
Accelerating Stochastic Probabilistic Inference—0
Amortized Proximal Optimization—0
Generalized Optimistic Methods for Convex-Concave Saddle Point ProblemsCode0
A Mini-Block Fisher Method for Deep Neural Networks—0
Communication-Efficient Stochastic Zeroth-Order Optimization for Federated LearningCode1
Accelerated Projected Gradient Method for the Optimization of Cell-Free Massive MIMO Downlink—0
SCORE: Approximating Curvature Information under Self-Concordant Regularization—0
Newton methods based convolution neural networks using parallel processing—0
Basis Matters: Better Communication-Efficient Second Order Methods for Federated Learning—0
Provable Regret Bounds for Deep Online Learning and Control—0
KKT Conditions, First-Order and Second-Order Optimization, and Distributed Optimization: Tutorial and Survey—0
SLIM-QN: A Stochastic, Light, Momentumized Quasi-Newton Optimizer for Deep Neural Networks—0
Second-Order Neural ODE OptimizerCode1
Nonlinear matrix recovery using optimization on the Grassmann manifoldCode0
Doubly Adaptive Scaled Algorithm for Machine Learning Using Second-Order Information—0
Structured second-order methods via natural gradient descent—0
M-FAC: Efficient Matrix-Free Approximations of Second-Order InformationCode1
Bilinear Parameterization for Non-Separable Singular Value Penalties—0
LocoProp: Enhancing BackProp via Local Loss Optimization—0
Tensor Normal Training for Deep Learning ModelsCode0
FedNL: Making Newton-Type Methods Applicable to Federated Learning—0
Exact Stochastic Second Order Deep Learning—0
Quasi-Newton Quasi-Monte Carlo for variational Bayes—0
Research of Damped Newton Stochastic Gradient Descent Method for Neural Network Training—0
Show:102550
← PrevPage 4 of 8Next →

No leaderboard results yet.