Optimization & Theory

Finding the Dominant Winning Ticket in Pre-Trained Language Models ACL 2022 Fine-tuning Language Models over Slow Networks using Activation Quantization with Guarantees NeurIPS 2022 Fine-Tuning Pre-trained Transformers into Decaying Fast Weights EMNLP 2022 FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness NeurIPS 2022 Flexible Neural Image Compression via Code Editing NeurIPS 2022 Flowformer: Linearizing Transformers with Conservation Flows ICML 2022 Focal and Global Knowledge Distillation for Detectors CVPR 2022 FOCUS: Flexible Optimizable Counterfactual Explanations for Tree Ensembles AAAI 2022 Foolish Crowds Support Benign Overfitting JMLR 2022 Forget-free Continual Learning with Winning Subnetworks ICML 2022 ∞-former: Infinite Memory Transformer ACL 2022 FourierNets enable the design of highly non-local optical encoders for computational imaging NeurIPS 2022 FP8 Quantization: The Power of the Exponent NeurIPS 2022 FPT: Improving Prompt Tuning Efficiency via Progressive Training EMNLP 2022 Fractional Adaptive Linear Units AAAI 2022 From Dense to Sparse: Contrastive Pruning for Better Pre-trained Language Model Compression AAAI 2022 From Fully Trained to Fully Random Embeddings: Improving Neural Machine Translation with Compact Word Embedding Tables AAAI 2022 From Gradient Flow on Population Loss to Learning with Stochastic Gradient Descent NeurIPS 2022 FrugalScore: Learning Cheaper, Lighter and Faster Evaluation Metrics for Automatic Text Generation ACL 2022 Fully-Connected Network on Noncompact Symmetric Space and Ridgelet Transform based on Helgason-Fourier Analysis ICML 2022 Fully Hyperbolic Neural Networks ACL 2022 GA-SAM: Gradient-Strength based Adaptive Sharpness-Aware Minimization for Improved Generalization EMNLP 2022 GBA: A Tuning-free Approach to Switch between Synchronous and Asynchronous Training for Recommendation Models NeurIPS 2022 General Cutting Planes for Bound-Propagation-Based Neural Network Verification NeurIPS 2022 Generalization Guarantee of Training Graph Convolutional Networks with Graph Topology Sampling ICML 2022