Optimization

DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learning ICML 2021 Do We Actually Need Dense Over-Parameterization? In-Time Over-Parameterization in Sparse Training ICML 2021 Do We Really Need Gold Samples for Sample Weighting Under Label Noise? WACV 2021 Dr Jekyll & Mr Hyde: the strange case of off-policy policy updates NeurIPS 2021 Drop-DTW: Aligning Common Signal Between Sequences While Dropping Outliers NeurIPS 2021 DSRNA: Differentiable Search of Robust Neural Architectures CVPR 2021 Dual Active Learning for Both Model and Data Selection IJCAI 2021 Dual Adaptivity: A Universal Algorithm for Minimizing the Adaptive Regret of Convex Functions NeurIPS 2021 Dual Projection Generative Adversarial Networks for Conditional Image Generation ICCV 2021 Dynamical Pose Estimation ICCV 2021 Dynamic Game Theoretic Neural Optimizer ICML 2021 Dynamic Planning and Learning under Recovering Rewards ICML 2021 Dynamic Sasvi: Strong Safe Screening for Norm-Regularized Least Squares NeurIPS 2021 Dynamic visualization for L1 fusion convex clustering in near-linear time UAI 2021 Dynamic Visual Reasoning by Learning Differentiable Physics Models from Video and Language NeurIPS 2021 Dynamic Weighted Learning for Unsupervised Domain Adaptation CVPR 2021 DynaTune: Dynamic Tensor Program Optimization in Deep Neural Network Compilation ICLR 2021 ECONOMIC HYPERPARAMETER OPTIMIZATION WITH BLENDED SEARCH STRATEGY ICLR 2021 EF21: A New, Simpler, Theoretically Better, and Practically Faster Error Feedback NeurIPS 2021 Effective and Efficient Vote Attack on Capsule Networks ICLR 2021 Effective Meta-Regularization by Kernelized Proximal Regularization NeurIPS 2021 Efficient Algorithms for Learning Depth-2 Neural Networks with General ReLU Activations NeurIPS 2021 Efficient Bandit Convex Optimization: Beyond Linear Losses COLT 2021 Efficient Combination of Rematerialization and Offloading for Training DNNs NeurIPS 2021 Efficient First-Order Contextual Bandits: Prediction, Allocation, and Triangular Discrimination NeurIPS 2021