Optimization & Theory

Practical Schemes for Finding Near-Stationary Points of Convex Finite-Sums AISTATS 2022 Predicting Attention Sparsity in Transformers ACL 2022 Prediction Difference Regularization against Perturbation for Neural Machine Translation ACL 2022 Principal Components Bias in Over-parameterized Linear Models, and its Manifestation in Deep Neural Networks JMLR 2022 Prior Gradient Mask Guided Pruning-Aware Fine-Tuning AAAI 2022 Private Adaptive Optimization with Side information ICML 2022 PrivateSNN: Privacy-Preserving Spiking Neural Networks AAAI 2022 Probing for the Usage of Grammatical Number ACL 2022 Probing Structured Pruning on Multilingual Pre-trained Models: Settings, Algorithms, and Efficiency ACL 2022 Probing via Prompting NAACL 2022 Programmatic Reinforcement Learning without Oracles ICLR 2022 Projective Manifold Gradient Layer for Deep Rotation Regression CVPR 2022 projUNN: efficient method for training deep networks with unitary matrices NeurIPS 2022 Pro-KD: Progressive Distillation by Following the Footsteps of the Teacher COLING 2022 Prompt Certified Machine Unlearning with Randomized Gradient Smoothing and Quantization NeurIPS 2022 Prompt Compression and Contrastive Conditioning for Controllability and Toxicity Reduction in Language Models EMNLP 2022 Proof of Learning: Towards a Practical Blockchain Consensus Mechanism Using Directed Guiding Gradients (Student Abstract) AAAI 2022 Proppo: a Message Passing Framework for Customizable and Composable Learning Algorithms NeurIPS 2022 Provable Acceleration of Heavy Ball beyond Quadratics for a Class of Polyak-Lojasiewicz Functions when the Non-Convexity is Averaged-Out ICML 2022 Provable Guarantees for Understanding Out-of-Distribution Detection AAAI 2022 Proximal and Federated Random Reshuffling ICML 2022 Proximal Denoiser for Convergent Plug-and-Play Optimization with Nonconvex Regularization ICML 2022 Proximal PanNet: A Model-Based Deep Network for Pansharpening AAAI 2022 ProxSkip: Yes! Local Gradient Steps Provably Lead to Communication Acceleration! Finally! ICML 2022 Prune and Tune Ensembles: Low-Cost Ensemble Learning with Sparse Independent Subnetworks AAAI 2022