Optimization

On the Adequacy of Untuned Warmup for Adaptive Optimization AAAI 2021 On the Convergence of Communication-Efficient Local SGD for Federated Learning AAAI 2021 On the Convergence of Step Decay Step-Size for Stochastic Optimization NeurIPS 2021 On the Predictability of Pruning Across Scales ICML 2021 On the Proof of Global Convergence of Gradient Descent for Deep ReLU Networks with Linear Widths ICML 2021 On the Theory of Implicit Deep Learning: Global Convergence with Implicit Layers ICLR 2021 Opening the Blackbox: Accelerating Neural Differential Equations by Regularizing Internal Solver Heuristics ICML 2021 OpEvo: An Evolutionary Method for Tensor Operator Optimization AAAI 2021 Optimal Gradient Checkpoint Search for Arbitrary Computation Graphs CVPR 2021 Optimization of Graph Neural Networks: Implicit Acceleration by Skip Connections and More Depth ICML 2021 OTA: Optimal Transport Assignment for Object Detection CVPR 2021 Penalty Method for Inversion-Free Deep Bilevel Optimization ACML 2021 Permute, Quantize, and Fine-Tune: Efficient Compression of Neural Networks CVPR 2021 PET: Optimizing Tensor Programs with Partially Equivalent Transformations and Automated Corrections OSDI 2021 Positive-Negative Momentum: Manipulating Stochastic Gradient Noise to Improve Generalization ICML 2021 Principal Bit Analysis: Autoencoding with Schur-Concave Loss ICML 2021 Projection Robust Wasserstein Barycenters ICML 2021 Reducing Neural Network Parameter Initialization Into an SMT Problem (Student Abstract) AAAI 2021 Refining BERT Embeddings for Document Hashing via Mutual Information Maximization EMNLP 2021 Regularizing Generative Adversarial Networks Under Limited Data CVPR 2021 ReNAS: Relativistic Evaluation of Neural Architecture Search CVPR 2021 Residual Echo and Noise Cancellation with Feature Attention Module and Multi-Domain Loss Function Interspeech 2021 Revealing the Structure of Deep Neural Networks via Convex Duality ICML 2021 Revisiting the Role of Euler Numerical Integration on Acceleration and Stability in Convex Optimization AISTATS 2021 Riggable 3D Face Reconstruction via In-Network Optimization CVPR 2021