← Optimization & Theory
Machine Learning › Optimization & Theory ›

Neural Network Optimization

3648 directly classified papers

Papers per year

Papers

Learning with Hyperspherical Uniformity AISTATS 2021
Stable ResNet AISTATS 2021
Phase Diagram for Two-layer ReLU Neural Networks at Infinite-width Limit JMLR 2021
Implicit Self-Regularization in Deep Neural Networks: Evidence from Random Matrix Theory and Implications for Learning JMLR 2021
Approximate Newton Methods JMLR 2021
Conflicting Bundles: Adapting Architectures Towards the Improved Training of Deep Neural Networks WACV 2021
Phase-Wise Parameter Aggregation for Improving SGD Optimization WACV 2021
Fast Fourier Intrinsic Network WACV 2021
Multi-Grained Knowledge Distillation for Named Entity Recognition NAACL 2021
Addressing the Vulnerability of NMT in Input Perturbations NAACL 2021
On the Transformer Growth for Progressive BERT Training NAACL 2021
Discovering Better Model Architectures for Medical Query Understanding NAACL 2021
Stabilizing Equilibrium Models by Jacobian Regularization ICML 2021
SMG: A Shuffling Gradient-Based Method with Momentum ICML 2021
High-Performance Large-Scale Image Recognition Without Normalization ICML 2021
Accelerating Gossip SGD with Periodic Global Averaging ICML 2021
Catformer: Designing Stable Transformers via Sensitivity Analysis ICML 2021
Debiasing a First-order Heuristic for Approximate Bi-level Optimization ICML 2021
Selfish Sparse RNN Training ICML 2021
Optimization Planning for 3D ConvNets ICML 2021
Catastrophic Fisher Explosion: Early Phase Fisher Matrix Impacts Generalization ICML 2021
Unbiased Gradient Estimation in Unrolled Computation Graphs with Persistent Evolution Strategies ICML 2021
Efficient Differentiable Simulation of Articulated Bodies ICML 2021
PAGE: A Simple and Optimal Probabilistic Gradient Estimator for Nonconvex Optimization ICML 2021
Parallelizing Legendre Memory Unit Training ICML 2021