neural network optimization

OpEvo: An Evolutionary Method for Tensor Operator Optimization AAAI 2021 Optimal ANN-SNN Conversion for Fast and Accurate Inference in Deep Spiking Neural Networks IJCAI 2021 Optimization of Graph Neural Networks: Implicit Acceleration by Skip Connections and More Depth ICML 2021 Optimization Planning for 3D ConvNets ICML 2021 Optimizing Deeper Transformers on Small Datasets ACL 2021 Orthogonal Over-Parameterized Training CVPR 2021 Particle Dual Averaging: Optimization of Mean Field Neural Network with Global Convergence Rate Analysis NeurIPS 2021 Path-BN: Towards effective batch normalization in the Path Space for ReLU networks UAI 2021 Phase Diagram for Two-layer ReLU Neural Networks at Infinite-width Limit JMLR 2021 Phase-Wise Parameter Aggregation for Improving SGD Optimization WACV 2021 Post-training Quantization with Multiple Points: Mixed Precision without Mixed Precision AAAI 2021 Post-Training Sparsity-Aware Quantization NeurIPS 2021 Quantifying the Benefit of Using Differentiable Learning over Tangent Kernels ICML 2021 Rank & Sort Loss for Object Detection and Instance Segmentation ICCV 2021 RAST: Domain-Robust Dialogue Rewriting as Sequence Tagging EMNLP 2021 Regularizing Neural Networks via Adversarial Model Perturbation CVPR 2021 Reliably Fast Adversarial Training via Latent Adversarial Perturbation ICCV 2021 ResNEsts and DenseNEsts: Block-based DNN Models with Improved Representation Guarantees NeurIPS 2021 Retinex-Inspired Unrolling With Cooperative Prior Architecture Search for Low-Light Image Enhancement CVPR 2021 Reverse engineering learned optimizers reveals known and novel mechanisms NeurIPS 2021 Revisiting Weight Initialization of Deep Neural Networks ACML 2021 RT3D: Achieving Real-Time Execution of 3D Convolutional Neural Networks on Mobile Devices AAAI 2021 S$^3$: Sign-Sparse-Shift Reparametrization for Effective Training of Low-bit Shift Networks NeurIPS 2021 SA-BNN: State-Aware Binary Neural Network AAAI 2021 SAPE: Spatially-Adaptive Progressive Encoding for Neural Optimization NeurIPS 2021