Neural Network Optimization

Phase Diagram for Two-layer ReLU Neural Networks at Infinite-width Limit JMLR 2021 Phase-Wise Parameter Aggregation for Improving SGD Optimization WACV 2021 Pi-NAS: Improving Neural Architecture Search by Reducing Supernet Training Consistency Shift ICCV 2021 Practical Real Time Recurrent Learning with a Sparse Approximation ICLR 2021 Prefix-Tuning: Optimizing Continuous Prompts for Generation ACL 2021 Prioritized Architecture Sampling With Monto-Carlo Tree Search CVPR 2021 Probing Word Translations in the Transformer and Trading Decoder for Encoder Layers NAACL 2021 Progressive Feature Interaction Search for Deep Sparse Network NeurIPS 2021 Provable Generalization of SGD-trained Neural Networks of Any Width in the Presence of Adversarial Label Noise ICML 2021 Provable Memorization via Deep Neural Networks using Sub-linear Parameters COLT 2021 Proxy Convexity: A Unified Framework for the Analysis of Neural Networks Trained by Gradient Descent NeurIPS 2021 Pyramid Architecture Search for Real-Time Image Deblurring ICCV 2021 Quasi-global Momentum: Accelerating Decentralized Deep Learning on Heterogeneous Data ICML 2021 Raise a Child in Large Language Model: Towards Effective and Generalizable Fine-tuning EMNLP 2021 Randomized Deep Structured Prediction for Discourse-Level Processing EACL 2021 Random Shuffling Beats SGD Only After Many Epochs on Ill-Conditioned Problems NeurIPS 2021 RDI-Net: Relational Dynamic Inference Networks ICCV 2021 Reasoning in Dialog: Improving Response Generation by Context Reading Comprehension AAAI 2021 Recovering AES Keys with a Deep Cold Boot Attack ICML 2021 Rectification-Based Knowledge Retention for Continual Learning CVPR 2021 Reducing Neural Network Parameter Initialization Into an SMT Problem (Student Abstract) AAAI 2021 Regularization Matters: A Nonparametric Perspective on Overparametrized Neural Network AISTATS 2021 Regularizing Neural Networks via Adversarial Model Perturbation CVPR 2021 Relating Adversarially Robust Generalization to Flat Minima ICCV 2021 Relative Flatness and Generalization NeurIPS 2021