Optimization & Theory

Interpreting Super-Resolution Networks With Local Attribution Maps CVPR 2021 Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning ACL 2021 Is Each Layer Non-trivial in CNN? (Student Abstract) AAAI 2021 Isometric Multi-Shape Matching CVPR 2021 Iso-Points: Optimizing Neural Implicit Surfaces With Hybrid Representations CVPR 2021 Iterative Deep Model Compression and Acceleration in the Frequency Domain ACML 2021 Joint inference and input optimization in equilibrium networks NeurIPS 2021 Just Ask! Evaluating Machine Translation by Asking and Answering Questions EMNLP 2021 (Just) A Spoonful of Refinements Helps the Registration Error Go Down ICCV 2021 Kernel Operations on the GPU, with Autodiff, without Memory Overflows JMLR 2021 Knowledge Evolution in Neural Networks CVPR 2021 K-shot NAS: Learnable Weight-Sharing for NAS with K-shot Supernets ICML 2021 KSM: Fast Multiple Task Adaption via Kernel-Wise Soft Mask Learning CVPR 2021 Label Noise SGD Provably Prefers Flat Global Minimizers NeurIPS 2021 Landmark Regularization: Ranking Guided Super-Net Training in Neural Architecture Search CVPR 2021 Language Resource Efficient Learning for Captioning EMNLP 2021 Large Batch Optimization for Deep Learning Using New Complete Layer-Wise Adaptive Rate Scaling AAAI 2021 Large Norms of CNN Layers Do Not Hurt Adversarial Robustness AAAI 2021 Large-Scale Learning with Fourier Features and Tensor Decompositions NeurIPS 2021 Large Scale Multi-Illuminant (LSMI) Dataset for Developing White Balance Algorithm Under Mixed Illumination ICCV 2021 Large Scale Private Learning via Low-rank Reparametrization ICML 2021 LassoNet: A Neural Network with Feature Sparsity JMLR 2021 Last iterate convergence of SGD for Least-Squares in the Interpolation regime. NeurIPS 2021 Layer-Wise Neural Network Compression via Layer Fusion ACML 2021 Layerwise Optimization by Gradient Decomposition for Continual Learning CVPR 2021