Neural Network Optimization

A Single-Timescale Method for Stochastic Bilevel Optimization AISTATS 2022 A Solver + Gradient Descent Training Algorithm for Deep Neural Networks IJCAI 2022 Associated Learning: an Alternative to End-to-End Backpropagation that Works on CNN, RNN, and Transformer ICLR 2022 A Stochastic Bundle Method for Interpolation JMLR 2022 A Stochastic Momentum Accelerated Quasi-Newton Method for Neural Networks (Student Abstract) AAAI 2022 A study on constraining Connectionist Temporal Classification for temporal audio alignment Interspeech 2022 A Theoretical Framework for Inference Learning NeurIPS 2022 Attentive Recurrent Network for Low-Latency Active Noise Control Interspeech 2022 A Unified Framework for Implicit Sinkhorn Differentiation CVPR 2022 AutoBERT-Zero: Evolving BERT Backbone from Scratch AAAI 2022 AutoCFR: Learning to Design Counterfactual Regret Minimization Algorithms AAAI 2022 Automated Progressive Learning for Efficient Training of Vision Transformers CVPR 2022 Automatic Mean Opinion Score Estimation with Temporal Modulation Features on Gammatone Filterbank for Speech Assessment Interspeech 2022 Auto-X3D: Ultra-Efficient Video Understanding via Finer-Grained Neural Architecture Search WACV 2022 A Variant of Anderson Mixing with Minimal Memory Size NeurIPS 2022 BaLeNAS: Differentiable Architecture Search via the Bayesian Learning Rule CVPR 2022 Batch Normalization Preconditioning for Neural Network Training JMLR 2022 b-DARTS: Beta-Decay Regularization for Differentiable Architecture Search CVPR 2022 Benign Overfitting in Two-layer Convolutional Neural Networks NeurIPS 2022 Benign Underfitting of Stochastic Gradient Descent NeurIPS 2022 Better Parameter-Free Stochastic Optimization with ODE Updates for Coin-Betting AAAI 2022 Better SGD using Second-order Momentum NeurIPS 2022 Beyond accuracy: generalization properties of bio-plausible temporal credit assignment rules NeurIPS 2022 Beyond Sub-Gaussian Noises: Sharp Concentration Analysis for Stochastic Gradient Descent JMLR 2022 Bidirectional Learning for Offline Infinite-width Model-based Optimization NeurIPS 2022