SOTAVerified

Second-order methods

Use second-order statistics to process data.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 101–150 of 181 papers

TitleStatusHype
FedNL: Making Newton-Type Methods Applicable to Federated Learning—0
Tensor Normal Training for Deep Learning ModelsCode0
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
A Distributed Optimisation Framework Combining Natural Gradient with Hessian-Free for Discriminative Sequence Training—0
Learning-Augmented Sketches for Hessians—0
Distributed Second Order Methods with Fast Rates and Compressed Communication—0
Kronecker-factored Quasi-Newton Methods for Deep Learning—0
A Chaos Theory Approach to Understand Neural Network Optimization—0
Adaptive Single-Pass Stochastic Gradient Descent in Input Sparsity Time—0
Noise and Fluctuation of Finite Learning Rate Stochastic Gradient Descent—0
Utility Maximization for Large-Scale Cell-Free Massive MIMO Downlink—0
Second-order Neural Network Training Using Complex-step Directional Derivative—0
Debiasing Distributed Second Order Optimization with Surrogate Sketching and Scaled Regularization—0
Second-Order Information in Non-Convex Stochastic Optimization: Power and Limitations—0
When Does Preconditioning Help or Hurt Generalization?—0
A block coordinate descent optimizer for classification problems exploiting convexity—0
Enhance Curvature Information by Structured Stochastic Quasi-Newton Methods—0
Learning Rates as a Function of Batch Size: A Random Matrix Theory Approach to Neural Network TrainingCode0
SONIA: A Symmetric Blockwise Truncated Optimization Algorithm—0
Asymptotic Analysis of Conditioned Stochastic Gradient DescentCode0
On the Promise of the Stochastic Generalized Gauss-Newton Method for Training DNNsCode0
Critical Point-Finding Methods Reveal Gradient-Flat Regions of Deep Network Losses—0
Stochastic Subspace Cubic Newton Method—0
DDPNOpt: Differential Dynamic Programming Neural Optimizer—0
Newtonian Monte Carlo: single-site MCMC meets second-order gradient methodsCode0
Curvature-corrected learning dynamics in deep neural networks—0
Stochastic Newton and Cubic Newton Methods with Simple Local Linear-Quadratic RatesCode0
Hierarchical model-based policy optimization: from actions to action sequences and back—0
Implementation of a modified Nesterov's Accelerated quasi-Newton Method on Tensorflow—0
Fast and Furious Convergence: Stochastic Second Order Methods under InterpolationCode0
EXACT ANALYSIS OF CURVATURE CORRECTED LEARNING DYNAMICS IN DEEP LINEAR NETWORKS—0
Quasi-Newton Optimization Methods For Deep Learning Applications—0
Practical Newton-Type Distributed Learning using Gradient Based Approximations—0
Meta-descent for Online, Continual Prediction—0
SGD momentum optimizer with step estimation by online parabola modelCode0
Limitations of the Empirical Fisher Approximation for Natural Gradient DescentCode0
Gram-Gauss-Newton Method: Learning Overparameterized Neural Networks for Regression Problems—0
LIBS2ML: A Library for Scalable Second Order Machine Learning AlgorithmsCode0
Improving SGD convergence by online linear regression of gradients in multiple statistically relevant directionsCode0
Stochastic Trust Region Inexact Newton Method for Large-scale Machine LearningCode0
Bilinear Parameterization For Differentiable Rank-Regularization—0
Deep Reinforcement Learning via L-BFGS Optimization—0
Large batch size training of neural networks with adversarial training and second-order informationCode0
Stochastic Second-order Methods for Non-convex Optimization with Inexact Hessian and Gradient—0
A Distributed Second-Order Algorithm You Can Trust—0
Online Second Order Methods for Non-Convex Stochastic OptimizationsCode0
GPU Accelerated Sub-Sampled Newton's Method—0
The Many Faces of Exponential Weights in Online Learning—0
Show:102550
← PrevPage 3 of 4Next →

No leaderboard results yet.