Optimization & Theory

The Hintons in your Neural Network: a Quantum Field Theory View of Deep Learning ICML 2021 The Implicit Bias for Adaptive Optimization Algorithms on Homogeneous Neural Networks ICML 2021 The Implicit Bias of Minima Stability: A View from Function Space NeurIPS 2021 The Lipschitz Constant of Self-Attention ICML 2021 The Lottery Ticket Hypothesis for Object Recognition CVPR 2021 The Lottery Tickets Hypothesis for Supervised and Self-Supervised Pre-Training in Computer Vision Models CVPR 2021 The Low-Resource Double Bind: An Empirical Study of Pruning for Low-Resource Machine Translation EMNLP 2021 The Neural Tangent Link Between CNN Denoisers and Non-Local Filters CVPR 2021 The NiuTrans System for the WMT 2021 Efficiency Task EMNLP 2021 The Spectrum of Fisher Information of Deep Networks Achieving Dynamical Isometry AISTATS 2021 The staircase property: How hierarchical structure can guide deep learning NeurIPS 2021 THOR, Trace-based Hardware-driven Layer-Oriented Natural Gradient Descent Computation AAAI 2021 Three Operator Splitting with Subgradients, Stochastic Gradients, and Adaptive Learning Rates NeurIPS 2021 Tight Bounds on the Smallest Eigenvalue of the Neural Tangent Kernel for Deep ReLU Networks ICML 2021 Tightening Robustness Verification of Convolutional Neural Networks with Fine-Grained Linear Approximation AAAI 2021 Tilting the playing field: Dynamical loss functions for machine learning ICML 2021 Time Adaptive Recurrent Neural Network CVPR 2021 Time-Multiplexed Coded Aperture Imaging: Learned Coded Aperture and Pixel Exposures for Compressive Imaging Systems ICCV 2021 To Optimize, or Not to Optimize, That Is the Question: TelU-KU Models for WMT21 Large-Scale Multilingual Machine Translation EMNLP 2021 Topological Detection of Trojaned Neural Networks NeurIPS 2021 Topological Uncertainty: Monitoring Trained Neural Networks through Persistence of Activation Graphs IJCAI 2021 To Ship or Not to Ship: An Extensive Evaluation of Automatic Metrics for Machine Translation EMNLP 2021 Toward Better Generalization Bounds with Locally Elastic Stability ICML 2021 Towards Compact CNNs via Collaborative Compression CVPR 2021 Towards Efficient Tensor Decomposition-Based DNN Model Compression With Optimization Framework CVPR 2021