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
Sub-sampled Newton Methods with Non-uniform Sampling—0
The Challenges of the Nonlinear Regime for Physics-Informed Neural Networks—0
The Many Faces of Exponential Weights in Online Learning—0
Unlocking FedNL: Self-Contained Compute-Optimized Implementation—0
Utility Maximization for Large-Scale Cell-Free Massive MIMO Downlink—0
Explicit Second-Order Min-Max Optimization Methods with Optimal Convergence Guarantee—0
Extra-Newton: A First Approach to Noise-Adaptive Accelerated Second-Order Methods—0
Faster Differentially Private Convex Optimization via Second-Order Methods—0
FedNL: Making Newton-Type Methods Applicable to Federated Learning—0
FedOSAA: Improving Federated Learning with One-Step Anderson Acceleration—0
Fed-Sophia: A Communication-Efficient Second-Order Federated Learning Algorithm—0
First and Second Order Methods for Online Convolutional Dictionary Learning—0
GP-FL: Model-Based Hessian Estimation for Second-Order Over-the-Air Federated Learning—0
GPU Accelerated Sub-Sampled Newton's Method—0
Gradient-Boosted Based Structured and Unstructured Learning—0
Gradient Norm Regularization Second-Order Algorithms for Solving Nonconvex-Strongly Concave Minimax Problems—0
Hierarchical model-based policy optimization: from actions to action sequences and back—0
Highly Efficient Hierarchical Online Nonlinear Regression Using Second Order Methods—0
Implementation of a modified Nesterov's Accelerated quasi-Newton Method on Tensorflow—0
Improving Stochastic Cubic Newton with Momentum—0
Inverse-Free Fast Natural Gradient Descent Method for Deep Learning—0
Jorge: Approximate Preconditioning for GPU-efficient Second-order Optimization—0
KKT Conditions, First-Order and Second-Order Optimization, and Distributed Optimization: Tutorial and Survey—0
Kronecker-Factored Approximate Curvature for Physics-Informed Neural Networks—0
Kronecker-factored Quasi-Newton Methods for Deep Learning—0
Krylov Cubic Regularized Newton: A Subspace Second-Order Method with Dimension-Free Convergence Rate—0
Large Scale Empirical Risk Minimization via Truncated Adaptive Newton Method—0
Learning-Augmented Sketches for Hessians—0
Meta-descent for Online, Continual Prediction—0
Minibatching Offers Improved Generalization Performance for Second Order Optimizers—0
Mirror Prox Algorithm for Large-Scale Cell-Free Massive MIMO Uplink Power Control—0
Near-Optimal Nonconvex-Strongly-Convex Bilevel Optimization with Fully First-Order Oracles—0
Nesterov's Acceleration For Approximate Newton—0
Nestrov's Acceleration For Second Order Method—0
Newton methods based convolution neural networks using parallel processing—0
Newton-Stein Method: An optimization method for GLMs via Stein's Lemma—0
Newton-Stein Method: A Second Order Method for GLMs via Stein's Lemma—0
On backpropagating Hessians through ODEs—0
On the efficiency of Stochastic Quasi-Newton Methods for Deep Learning—0
On the importance of initialization and momentum in deep learning—0
On The Temporal Domain of Differential Equation Inspired Graph Neural Networks—0
Oracle Complexity of Second-Order Methods for Finite-Sum Problems—0
Practical Newton-Type Distributed Learning using Gradient Based Approximations—0
Exact, Tractable Gauss-Newton Optimization in Deep Reversible Architectures Reveal Poor GeneralizationCode0
Learning Rates as a Function of Batch Size: A Random Matrix Theory Approach to Neural Network TrainingCode0
SGD momentum optimizer with step estimation by online parabola modelCode0
Fast and Furious Convergence: Stochastic Second Order Methods under InterpolationCode0
Statistical Inference of Constrained Stochastic Optimization via Sketched Sequential Quadratic ProgrammingCode0
SGD with Partial Hessian for Deep Neural Networks OptimizationCode0
Sharpened Lazy Incremental Quasi-Newton MethodCode0
Show:102550
← PrevPage 3 of 4Next →

No leaderboard results yet.