neural network optimization

Accelerating Gossip SGD with Periodic Global Averaging ICML 2021 ACMo: Angle-Calibrated Moment Methods for Stochastic Optimization AAAI 2021 A Compression-Compilation Co-Design Framework Towards Real-Time Object Detection on Mobile Devices AAAI 2021 Activate or Not: Learning Customized Activation CVPR 2021 ADAHESSIAN: An Adaptive Second Order Optimizer for Machine Learning AAAI 2021 Adaptive Proximal Gradient Methods for Structured Neural Networks NeurIPS 2021 Ada-Segment: Automated Multi-loss Adaptation for Panoptic Segmentation AAAI 2021 AdderSR: Towards Energy Efficient Image Super-Resolution CVPR 2021 A Deep Conditioning Treatment of Neural Networks ALT 2021 Adversarial Regularization as Stackelberg Game: An Unrolled Optimization Approach EMNLP 2021 Align, then memorise: the dynamics of learning with feedback alignment ICML 2021 A Modular Analysis of Provable Acceleration via Polyak’s Momentum: Training a Wide ReLU Network and a Deep Linear Network ICML 2021 Analytic Insights into Structure and Rank of Neural Network Hessian Maps NeurIPS 2021 An Empirical Study on Hyperparameter Optimization for Fine-Tuning Pre-trained Language Models ACL 2021 An Exponential Improvement on the Memorization Capacity of Deep Threshold Networks NeurIPS 2021 An Improved Single Step Non-Autoregressive Transformer for Automatic Speech Recognition Interspeech 2021 An Optimistic Acceleration of AMSGrad for Nonconvex Optimization ACML 2021 An optimization and generalization analysis for max-pooling networks UAI 2021 A PAC-Bayesian Approach to Generalization Bounds for Graph Neural Networks ICLR 2021 ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning of Deep Neural Networks ICML 2021 A self consistent theory of Gaussian Processes captures feature learning effects in finite CNNs NeurIPS 2021 A Sliced Wasserstein Loss for Neural Texture Synthesis CVPR 2021 Attention is not all you need: pure attention loses rank doubly exponentially with depth ICML 2021 Auction Learning as a Two-Player Game ICLR 2021 A Unified Analysis of First-Order Methods for Smooth Games via Integral Quadratic Constraints JMLR 2021