neural network optimization

To Fold or Not to Fold: a Necessary and Sufficient Condition on Batch-Normalization Layers Folding IJCAI 2022 To update or not to update? Neurons at equilibrium in deep models NeurIPS 2022 Toward Equation of Motion for Deep Neural Networks: Continuous-time Gradient Descent and Discretization Error Analysis NeurIPS 2022 Towards Better Plasticity-Stability Trade-Off in Incremental Learning: A Simple Linear Connector CVPR 2022 Towards Deepening Graph Neural Networks: A GNTK-based Optimization Perspective ICLR 2022 Towards Efficient and Scalable Sharpness-Aware Minimization CVPR 2022 Towards Fully Sparse Training: Information Restoration with Spatial Similarity AAAI 2022 Towards Light-Weight and Real-Time Line Segment Detection AAAI 2022 Train Flat, Then Compress: Sharpness-Aware Minimization Learns More Compressible Models EMNLP 2022 Training Quantised Neural Networks With STE Variants: The Additive Noise Annealing Algorithm CVPR 2022 Training Structured Neural Networks Through Manifold Identification and Variance Reduction ICLR 2022 Transformers from an Optimization Perspective NeurIPS 2022 Transition to Linearity of Wide Neural Networks is an Emerging Property of Assembling Weak Models ICLR 2022 TREC: Transient Redundancy Elimination-based Convolution NeurIPS 2022 Understanding Deep Contrastive Learning via Coordinate-wise Optimization NeurIPS 2022 Understanding Stochastic Optimization Behavior at the Layer Update Level (Student Abstract) AAAI 2022 Unity: Accelerating DNN Training Through Joint Optimization of Algebraic Transformations and Parallelization OSDI 2022 Walle: An End-to-End, General-Purpose, and Large-Scale Production System for Device-Cloud Collaborative Machine Learning OSDI 2022 Warmstart Approach for Accelerating Deep Image Prior Reconstruction in Dynamic Tomography MIDL 2022 What Can Linear Interpolation of Neural Network Loss Landscapes Tell Us? ICML 2022 When To Prune? A Policy Towards Early Structural Pruning CVPR 2022 Who Says Elephants Can’t Run: Bringing Large Scale MoE Models into Cloud Scale Production EMNLP 2022 Zero Stability Well Predicts Performance of Convolutional Neural Networks AAAI 2022 α-IoU: A Family of Power Intersection over Union Losses for Bounding Box Regression NeurIPS 2021 Accelerating Continuous Normalizing Flow with Trajectory Polynomial Regularization AAAI 2021