conftrace_

learning rate

192 papers

Explore in graph

Also known as

LR

Co-occurring keywords

stochastic gradient descent (1091) neural network optimization (1293) gradient descent (1144) convergence rate (607) convergence analysis (395) stochastic optimization (1060) online learning (1777) kernel methods (1097) neural network (6616) regret bound (1926)

Papers

Statistical Rates of Convergence for Functional Partially Linear Support Vector Machines for Classification JMLR 2022
On the Benefits of Large Learning Rates for Kernel Methods COLT 2022
On Non-local Convergence Analysis of Deep Linear Networks ICML 2022
Three-stage Evolution and Fast Equilibrium for SGD with Non-degerate Critical Points ICML 2022
Convergence Rates of Non-Convex Stochastic Gradient Descent Under a Generic Lojasiewicz Condition and Local Smoothness ICML 2022
Defending against Backdoors in Federated Learning with Robust Learning Rate AAAI 2021
Catastrophic Fisher Explosion: Early Phase Fisher Matrix Impacts Generalization ICML 2021
MetaGrad: Adaptation using Multiple Learning Rates in Online Learning JMLR 2021
Learning by Turning: Neural Architecture Aware Optimisation ICML 2021
An Inertial Newton Algorithm for Deep Learning JMLR 2021
High-probability Bounds for Non-Convex Stochastic Optimization with Heavy Tails NIPS 2021
Generalization Performance of Multi-pass Stochastic Gradient Descent with Convex Loss Functions JMLR 2021
Continuous Time Analysis of Momentum Methods JMLR 2021
A Unified Convergence Analysis for Shuffling-Type Gradient Methods JMLR 2021
Label Noise SGD Provably Prefers Flat Global Minimizers NIPS 2021
Dual Adaptivity: A Universal Algorithm for Minimizing the Adaptive Regret of Convex Functions NIPS 2021
On the Adequacy of Untuned Warmup for Adaptive Optimization AAAI 2021
AutoLR: Layer-wise Pruning and Auto-tuning of Learning Rates in Fine-tuning of Deep Networks AAAI 2021
SGD Generalizes Better Than GD (And Regularization Doesn’t Help) COLT 2021
How Data Augmentation affects Optimization for Linear Regression NIPS 2021
SGD for Structured Nonconvex Functions: Learning Rates, Minibatching and Interpolation AISTATS 2021
Fast rates for prediction with limited expert advice NIPS 2021
On the Validity of Modeling SGD with Stochastic Differential Equations (SDEs) NIPS 2021
Domain-Independent Dominance of Adaptive Methods CVPR 2021
Large Batch Optimization for Deep Learning Using New Complete Layer-Wise Adaptive Rate Scaling AAAI 2021