Optimization & Theory

Compressing Models With Few Samples: Mimicking Then Replacing CVPR 2022 Compression of Generative Pre-trained Language Models via Quantization ACL 2022 Computing Wasserstein-p Distance Between Images With Linear Cost CVPR 2022 Confidence Calibration for Intent Detection via Hyperspherical Space and Rebalanced Accuracy-Uncertainty Loss AAAI 2022 Confident Adaptive Language Modeling NeurIPS 2022 Continuation KD: Improved Knowledge Distillation through the Lens of Continuation Optimization EMNLP 2022 Controllable Dynamic Multi-Task Architectures CVPR 2022 Control Prefixes for Parameter-Efficient Text Generation EMNLP 2022 Convergence beyond the over-parameterized regime using Rayleigh quotients NeurIPS 2022 Convergence for score-based generative modeling with polynomial complexity NeurIPS 2022 Convergence Rates of Non-Convex Stochastic Gradient Descent Under a Generic Lojasiewicz Condition and Local Smoothness ICML 2022 Convex Analysis of the Mean Field Langevin Dynamics AISTATS 2022 Convolutional Neural Network Compression through Generalized Kronecker Product Decomposition AAAI 2022 Coordinate Descent on the Orthogonal Group for Recurrent Neural Network Training AAAI 2022 cosFormer: Rethinking Softmax In Attention ICLR 2022 COST-EFF: Collaborative Optimization of Spatial and Temporal Efficiency with Slenderized Multi-exit Language Models EMNLP 2022 DACT-BERT: Differentiable Adaptive Computation Time for an Efficient BERT Inference ACL 2022 DAdaQuant: Doubly-adaptive quantization for communication-efficient Federated Learning ICML 2022 Data-Efficient Structured Pruning via Submodular Optimization NeurIPS 2022 Data-Free Network Compression via Parametric Non-Uniform Mixed Precision Quantization CVPR 2022 DataMUX: Data Multiplexing for Neural Networks NeurIPS 2022 Data Selection Curriculum for Neural Machine Translation EMNLP 2022 Dataset Distillation by Matching Training Trajectories CVPR 2022 Dataset Distillation using Neural Feature Regression NeurIPS 2022 DAVINZ: Data Valuation using Deep Neural Networks at Initialization ICML 2022