Optimization & Theory

What happens if you treat ordinal ratings as interval data? Human evaluations in NLP are even more under-powered than you think EMNLP 2021 What Matters for On-Policy Deep Actor-Critic Methods? A Large-Scale Study ICLR 2021 When Are Solutions Connected in Deep Networks? NeurIPS 2021 When Attention Meets Fast Recurrence: Training Language Models with Reduced Compute EMNLP 2021 When Does Gradient Descent with Logistic Loss Find Interpolating Two-Layer Networks? JMLR 2021 When does gradient descent with logistic loss interpolate using deep networks with smoothed ReLU activations? COLT 2021 When Do You Need Billions of Words of Pretraining Data? ACL 2021 When False Positive is Intolerant: End-to-End Optimization with Low FPR for Multipartite Ranking NeurIPS 2021 Whitening and Second Order Optimization Both Make Information in the Dataset Unusable During Training, and Can Reduce or Prevent Generalization ICML 2021 Why Adversarial Interaction Creates Non-Homogeneous Patterns: A Pseudo-Reaction-Diffusion Model for Turing Instability AAAI 2021 Why resampling outperforms reweighting for correcting sampling bias with stochastic gradients ICLR 2021 Winning Lottery Tickets in Deep Generative Models AAAI 2021 WrapNet: Neural Net Inference with Ultra-Low-Precision Arithmetic ICLR 2021 YOLObile: Real-Time Object Detection on Mobile Devices via Compression-Compilation Co-Design AAAI 2021 You Only Look One-Level Feature CVPR 2021 Zen-NAS: A Zero-Shot NAS for High-Performance Image Recognition ICCV 2021 Zero-Shot Adversarial Quantization CVPR 2021 Zero Time Waste: Recycling Predictions in Early Exit Neural Networks NeurIPS 2021 A2dele: Adaptive and Attentive Depth Distiller for Efficient RGB-D Salient Object Detection CVPR 2020 AANet: Adaptive Aggregation Network for Efficient Stereo Matching CVPR 2020 A Batch Normalized Inference Network Keeps the KL Vanishing Away ACL 2020 Absum: Simple Regularization Method for Reducing Structural Sensitivity of Convolutional Neural Networks AAAI 2020 Abusive Language Detection using Syntactic Dependency Graphs EMNLP 2020 Accelerating Stratified Sampling SGD by Reconstructing Strata IJCAI 2020 Accelerating Training of Transformer-Based Language Models with Progressive Layer Dropping NeurIPS 2020