Optimization & Theory

Parameter-Efficient Mixture-of-Experts Architecture for Pre-trained Language Models COLING 2022 Paramixer: Parameterizing Mixing Links in Sparse Factors Works Better Than Dot-Product Self-Attention CVPR 2022 Partially-Random Initialization: A Smoking Gun for Binarization Hypothesis of BERT EMNLP 2022 Partitioned Gradient Matching-based Data Subset Selection for Compute-Efficient Robust ASR Training EMNLP 2022 Pass off Fish Eyes for Pearls: Attacking Model Selection of Pre-trained Models ACL 2022 PatchFormer: An Efficient Point Transformer With Patch Attention CVPR 2022 PatchUp: A Feature-Space Block-Level Regularization Technique for Convolutional Neural Networks AAAI 2022 Path Independent Equilibrium Models Can Better Exploit Test-Time Computation NeurIPS 2022 PATS: Sensitivity-aware Noisy Learning for Pretrained Language Models EMNLP 2022 Pay attention to your loss : understanding misconceptions about Lipschitz neural networks NeurIPS 2022 PCA-Based Knowledge Distillation Towards Lightweight and Content-Style Balanced Photorealistic Style Transfer Models CVPR 2022 PEAF: Learnable Power Efficient Analog Acoustic Features for Audio Recognition Interspeech 2022 Penalizing Gradient Norm for Efficiently Improving Generalization in Deep Learning ICML 2022 Perception Prioritized Training of Diffusion Models CVPR 2022 Permutation-Based SGD: Is Random Optimal? ICLR 2022 Phase Collapse in Neural Networks ICLR 2022 Phase Transition from Clean Training to Adversarial Training NeurIPS 2022 PipeGCN: Efficient Full-Graph Training of Graph Convolutional Networks with Pipelined Feature Communication ICLR 2022 PLATON: Pruning Large Transformer Models with Upper Confidence Bound of Weight Importance ICML 2022 Playing Lottery Tickets with Vision and Language AAAI 2022 POET: Training Neural Networks on Tiny Devices with Integrated Rematerialization and Paging ICML 2022 Polyhistor: Parameter-Efficient Multi-Task Adaptation for Dense Vision Tasks NeurIPS 2022 Post-Hoc Interpretation of Transformer Hyperparameters with Explainable Boosting Machines EMNLP 2022 Power-Law Escape Rate of SGD ICML 2022 Practical Adversarial Attacks on Spatiotemporal Traffic Forecasting Models NeurIPS 2022