Optimization & Theory

AutoLRS: Automatic Learning-Rate Schedule by Bayesian Optimization on the Fly ICLR 2021 Automated Log-Scale Quantization for Low-Cost Deep Neural Networks CVPR 2021 Automated Model Design and Benchmarking of Deep Learning Models for COVID-19 Detection with Chest CT Scans AAAI 2021 Automatic Text Evaluation through the Lens of Wasserstein Barycenters EMNLP 2021 Auto-NBA: Efficient and Effective Search Over the Joint Space of Networks, Bitwidths, and Accelerators ICML 2021 Avoiding Kernel Fixed Points: Computing with ELU and GELU Infinite Networks AAAI 2021 A Zeroth-Order Block Coordinate Descent Algorithm for Huge-Scale Black-Box Optimization ICML 2021 Bag of Tricks for Optimizing Transformer Efficiency EMNLP 2021 BASE Layers: Simplifying Training of Large, Sparse Models ICML 2021 Bayesian Algorithm Execution: Estimating Computable Properties of Black-box Functions Using Mutual Information ICML 2021 Bayesian Deep Learning via Subnetwork Inference ICML 2021 Bayesian Nested Neural Networks for Uncertainty Calibration and Adaptive Compression CVPR 2021 BCNet: Searching for Network Width With Bilaterally Coupled Network CVPR 2021 Benign Overfitting of Constant-Stepsize SGD for Linear Regression COLT 2021 BERT might be Overkill: A Tiny but Effective Biomedical Entity Linker based on Residual Convolutional Neural Networks EMNLP 2021 BERTTune: Fine-Tuning Neural Machine Translation with BERTScore ACL 2021 Better Fine-Tuning by Reducing Representational Collapse ICLR 2021 Better Training using Weight-Constrained Stochastic Dynamics ICML 2021 Beyond Preserved Accuracy: Evaluating Loyalty and Robustness of BERT Compression EMNLP 2021 Bi-GCN: Binary Graph Convolutional Network CVPR 2021 BinaryBERT: Pushing the Limit of BERT Quantization ACL 2021 Binary Graph Neural Networks CVPR 2021 Bit-Mixer: Mixed-Precision Networks With Runtime Bit-Width Selection ICCV 2021 Blocking-based Neighbor Sampling for Large-scale Graph Neural Networks IJCAI 2021 Block Pruning For Faster Transformers EMNLP 2021