← Optimization & Theory
Machine Learning › Optimization & Theory ›

Neural Network Optimization

3648 directly classified papers

Papers per year

Papers

GAML-BERT: Improving BERT Early Exiting by Gradient Aligned Mutual Learning EMNLP 2021
Enlivening Redundant Heads in Multi-head Self-attention for Machine Translation EMNLP 2021
Effects of Parameter Norm Growth During Transformer Training: Inductive Bias from Gradient Descent EMNLP 2021
MTAdam: Automatic Balancing of Multiple Training Loss Terms EMNLP 2021
Faster Meta Update Strategy for Noise-Robust Deep Learning CVPR 2021
Regularizing Neural Networks via Adversarial Model Perturbation CVPR 2021
Effective Sparsification of Neural Networks With Global Sparsity Constraint CVPR 2021
Layerwise Optimization by Gradient Decomposition for Continual Learning CVPR 2021
Time Adaptive Recurrent Neural Network CVPR 2021
Enhance Curvature Information by Structured Stochastic Quasi-Newton Methods CVPR 2021
Learning the Non-Differentiable Optimization for Blind Super-Resolution CVPR 2021
Prioritized Architecture Sampling With Monto-Carlo Tree Search CVPR 2021
SKFAC: Training Neural Networks With Faster Kronecker-Factored Approximate Curvature CVPR 2021
RPSRNet: End-to-End Trainable Rigid Point Set Registration Network Using Barnes-Hut 2D-Tree Representation CVPR 2021
Searching by Generating: Flexible and Efficient One-Shot NAS With Architecture Generator CVPR 2021
Progressive Feature Interaction Search for Deep Sparse Network NIPS 2021
Aligned Structured Sparsity Learning for Efficient Image Super-Resolution NIPS 2021
Deep Learning on a Data Diet: Finding Important Examples Early in Training NIPS 2021
Understanding and Improving Early Stopping for Learning with Noisy Labels NIPS 2021
Second-Order Neural ODE Optimizer NIPS 2021
Improving Deep Learning Interpretability by Saliency Guided Training NIPS 2021
Convolutional Normalization: Improving Deep Convolutional Network Robustness and Training NIPS 2021
Dynamics of Stochastic Momentum Methods on Large-scale, Quadratic Models NIPS 2021
Random Shuffling Beats SGD Only After Many Epochs on Ill-Conditioned Problems NIPS 2021
Reverse engineering learned optimizers reveals known and novel mechanisms NIPS 2021