Optimization

AutoInt: Automatic Integration for Fast Neural Volume Rendering CVPR 2021 AutoLRS: Automatic Learning-Rate Schedule by Bayesian Optimization on the Fly ICLR 2021 Automated Log-Scale Quantization for Low-Cost Deep Neural Networks CVPR 2021 Auto-NBA: Efficient and Effective Search Over the Joint Space of Networks, Bitwidths, and Accelerators ICML 2021 A Zeroth-Order Block Coordinate Descent Algorithm for Huge-Scale Black-Box Optimization ICML 2021 Boost Neural Networks by Checkpoints NeurIPS 2021 Bringing UMAP Closer to the Speed of Light with GPU Acceleration AAAI 2021 Closing the Gap: Tighter Analysis of Alternating Stochastic Gradient Methods for Bilevel Problems NeurIPS 2021 Connecting Sphere Manifolds Hierarchically for Regularization ICML 2021 ContactOpt: Optimizing Contact To Improve Grasps CVPR 2021 Continuous Wasserstein-2 Barycenter Estimation without Minimax Optimization ICLR 2021 Contrastive Neural Architecture Search With Neural Architecture Comparators CVPR 2021 Convergence rates and approximation results for SGD and its continuous-time counterpart COLT 2021 Convolutional Neural Network Pruning With Structural Redundancy Reduction CVPR 2021 Cooperative SGD: A Unified Framework for the Design and Analysis of Local-Update SGD Algorithms JMLR 2021 Corrected CBOW Performs as well as Skip-gram EMNLP 2021 Correlation-Aware Heuristic Search for Intelligent Virtual Machine Provisioning in Cloud Systems AAAI 2021 Cross Modal Focal Loss for RGBD Face Anti-Spoofing CVPR 2021 DDSAS: Dynamic and Differentiable Space-Architecture Search ACML 2021 DecentLaM: Decentralized Momentum SGD for Large-Batch Deep Training ICCV 2021 DeepLM: Large-Scale Nonlinear Least Squares on Deep Learning Frameworks Using Stochastic Domain Decomposition CVPR 2021 DeRF: Decomposed Radiance Fields CVPR 2021 Descending through a Crowded Valley - Benchmarking Deep Learning Optimizers ICML 2021 Differentiable Fluids with Solid Coupling for Learning and Control AAAI 2021 Direction Matters: On the Implicit Bias of Stochastic Gradient Descent with Moderate Learning Rate ICLR 2021