conftrace_
← Optimization & Theory
Machine Learning › Optimization & Theory ›

Neural Network Optimization

3,648 papers

Papers per year

Papers

A Contraction Theory Approach to Optimization Algorithms from Acceleration Flows AISTATS 2022
Implicitly Regularized RL with Implicit Q-values AISTATS 2022
A Single-Timescale Method for Stochastic Bilevel Optimization AISTATS 2022
AdaBlock: SGD with Practical Block Diagonal Matrix Adaptation for Deep Learning AISTATS 2022
Scaling and Scalability: Provable Nonconvex Low-Rank Tensor Completion AISTATS 2022
Super-Acceleration with Cyclical Step-sizes AISTATS 2022
Momentum Accelerates the Convergence of Stochastic AUPRC Maximization AISTATS 2022
Towards Statistical and Computational Complexities of Polyak Step Size Gradient Descent AISTATS 2022
Faster Single-loop Algorithms for Minimax Optimization without Strong Concavity AISTATS 2022
Masked Training of Neural Networks with Partial Gradients AISTATS 2022
Are All Linear Regions Created Equal? AISTATS 2022
Vanishing Curvature in Randomly Initialized Deep ReLU Networks AISTATS 2022
Low-Pass Filtering SGD for Recovering Flat Optima in the Deep Learning Optimization Landscape AISTATS 2022
LocoProp: Enhancing BackProp via Local Loss Optimization AISTATS 2022
On the Implicit Bias of Gradient Descent for Temporal Extrapolation AISTATS 2022
Implicit Parameter-free Online Learning with Truncated Linear Models ALT 2022
On the Last Iterate Convergence of Momentum Methods ALT 2022
Inductive Bias of Gradient Descent for Weight Normalized Smooth Homogeneous Neural Nets ALT 2022
Reinforcement Learning with Large Action Spaces for Neural Machine Translation COLING 2022
A Closer Look at Parameter Contributions When Training Neural Language and Translation Models COLING 2022
Adaptive Meta-learner via Gradient Similarity for Few-shot Text Classification COLING 2022
Speeding up Transformer Decoding via an Attention Refinement Network COLING 2022
Alleviating the Inequality of Attention Heads for Neural Machine Translation COLING 2022
On the Benefits of Large Learning Rates for Kernel Methods COLT 2022
ROOT-SGD: Sharp Nonasymptotics and Asymptotic Efficiency in a Single Algorithm COLT 2022