Neural Network Optimization

Continuized Accelerations of Deterministic and Stochastic Gradient Descents, and of Gossip Algorithms NeurIPS 2021 Continuous vs. Discrete Optimization of Deep Neural Networks NeurIPS 2021 Contributions of Transformer Attention Heads in Multi- and Cross-lingual Tasks ACL 2021 Convergence and Alignment of Gradient Descent with Random Backpropagation Weights NeurIPS 2021 Convergence of adaptive algorithms for constrained weakly convex optimization NeurIPS 2021 Convergence rates and approximation results for SGD and its continuous-time counterpart COLT 2021 Convergence Rates of Stochastic Gradient Descent under Infinite Noise Variance NeurIPS 2021 Convolutional Normalization: Improving Deep Convolutional Network Robustness and Training NeurIPS 2021 Cooperative Joint Attentive Network for Patient Outcome Prediction on Irregular Multi-Rate Multivariate Health Data IJCAI 2021 Coreference Resolution without Span Representations ACL 2021 Coupled Gradient Estimators for Discrete Latent Variables NeurIPS 2021 Coupled Oscillatory Recurrent Neural Network (coRNN): An accurate and (gradient) stable architecture for learning long time dependencies ICLR 2021 Credit Assignment in Neural Networks through Deep Feedback Control NeurIPS 2021 Critical Parameters for Scalable Distributed Learning with Large Batches and Asynchronous Updates AISTATS 2021 Cross-Camera Convolutional Color Constancy ICCV 2021 Cyclically Equivariant Neural Decoders for Cyclic Codes ICML 2021 Data-Efficient Alignment of Multimodal Sequences by Aligning Gradient Updates and Internal Feature Distributions WACV 2021 DCNAS: Densely Connected Neural Architecture Search for Semantic Image Segmentation CVPR 2021 DDPNOpt: Differential Dynamic Programming Neural Optimizer ICLR 2021 Debiasing a First-order Heuristic for Approximate Bi-level Optimization ICML 2021 DecentLaM: Decentralized Momentum SGD for Large-Batch Deep Training ICCV 2021 Deconstructing the Regularization of BatchNorm ICLR 2021 Deep Learning on a Data Diet: Finding Important Examples Early in Training NeurIPS 2021 Deep Networks and the Multiple Manifold Problem ICLR 2021 Deep Networks Provably Classify Data on Curves NeurIPS 2021