Optimization & Theory

Block-wise Word Embedding Compression Revisited: Better Weighting and Structuring EMNLP 2021 Boost Neural Networks by Checkpoints NeurIPS 2021 Bounds all around: training energy-based models with bidirectional bounds NeurIPS 2021 BoW Pooling: A Plug-and-Play Unit for Feature Aggregation of Point Clouds AAAI 2021 Bringing UMAP Closer to the Speed of Light with GPU Acceleration AAAI 2021 Building Reliable Explanations of Unreliable Neural Networks: Locally Smoothing Perspective of Model Interpretation CVPR 2021 BulletTrain: Accelerating Robust Neural Network Training via Boundary Example Mining NeurIPS 2021 CAKES: Channel-wise Automatic KErnel Shrinking for Efficient 3D Networks AAAI 2021 CAMERAS: Enhanced Resolution and Sanity Preserving Class Activation Mapping for Image Saliency CVPR 2021 CascadeBERT: Accelerating Inference of Pre-trained Language Models via Calibrated Complete Models Cascade EMNLP 2021 Cascaded Head-colliding Attention ACL 2021 CDFI: Compression-Driven Network Design for Frame Interpolation CVPR 2021 Certified Robustness to Programmable Transformations in LSTMs EMNLP 2021 Certifying Incremental Quadratic Constraints for Neural Networks via Convex Optimization L4DC 2021 Channel Permutations for N:M Sparsity NeurIPS 2021 Characterizing Structural Regularities of Labeled Data in Overparameterized Models ICML 2021 Chasing Sparsity in Vision Transformers: An End-to-End Exploration NeurIPS 2021 Checkerboard Context Model for Efficient Learned Image Compression CVPR 2021 CHIP: CHannel Independence-based Pruning for Compact Neural Networks NeurIPS 2021 CIDEr-R: Robust Consensus-based Image Description Evaluation EMNLP 2021 ClassSR: A General Framework to Accelerate Super-Resolution Networks by Data Characteristic CVPR 2021 Closing the Gap: Tighter Analysis of Alternating Stochastic Gradient Methods for Bilevel Problems NeurIPS 2021 Combined Depth Space Based Architecture Search for Person Re-Identification CVPR 2021 Combiner: Full Attention Transformer with Sparse Computation Cost NeurIPS 2021 Communication Efficient SGD via Gradient Sampling With Bayes Prior CVPR 2021