Neural Network Optimization

Auto-ReID: Searching for a Part-Aware ConvNet for Person Re-Identification ICCV 2019 Backprop with Approximate Activations for Memory-efficient Network Training NeurIPS 2019 Bag of Tricks for Image Classification with Convolutional Neural Networks CVPR 2019 Band-limited Training and Inference for Convolutional Neural Networks ICML 2019 BayesNAS: A Bayesian Approach for Neural Architecture Search ICML 2019 Beyond Backprop: Online Alternating Minimization with Auxiliary Variables ICML 2019 Biologically-Plausible Learning Algorithms Can Scale to Large Datasets ICLR 2019 Breaking Inter-Layer Co-Adaptation by Classifier Anonymization ICML 2019 Calibrated Stochastic Gradient Descent for Convolutional Neural Networks AAAI 2019 Can SGD Learn Recurrent Neural Networks with Provable Generalization? NeurIPS 2019 Capacity Control of ReLU Neural Networks by Basis-Path Norm AAAI 2019 Cascade RPN: Delving into High-Quality Region Proposal Network with Adaptive Convolution NeurIPS 2019 Catastrophic Forgetting Meets Negative Transfer: Batch Spectral Shrinkage for Safe Transfer Learning NeurIPS 2019 Cell-aware Stacked LSTMs for Modeling Sentences ACML 2019 Cheap Orthogonal Constraints in Neural Networks: A Simple Parametrization of the Orthogonal and Unitary Group ICML 2019 CircConv: A Structured Convolution with Low Complexity AAAI 2019 Combining Global Sparse Gradients with Local Gradients in Distributed Neural Network Training EMNLP 2019 Communication-Efficient Distributed Blockwise Momentum SGD with Error-Feedback NeurIPS 2019 Communication trade-offs for Local-SGD with large step size NeurIPS 2019 Compressing Convolutional Neural Networks via Factorized Convolutional Filters CVPR 2019 Computing Linear Restrictions of Neural Networks NeurIPS 2019 Context-adaptive Entropy Model for End-to-end Optimized Image Compression ICLR 2019 Continual and Multi-Task Architecture Search ACL 2019 Continuous-time Models for Stochastic Optimization Algorithms NeurIPS 2019 Control Batch Size and Learning Rate to Generalize Well: Theoretical and Empirical Evidence NeurIPS 2019