Neural Network Optimization

AFRNN: Stable RNN with Top Down Feedback and Antisymmetry ACML 2022 A Fully Single Loop Algorithm for Bilevel Optimization without Hessian Inverse AAAI 2022 A Gentle Introduction to Deep Nets and Opportunities for the Future ACL 2022 A global convergence theory for deep ReLU implicit networks via over-parameterization ICLR 2022 A Learning-based Iterative Control Framework for Controlling a Robot Arm with Pneumatic Artificial Muscles RSS 2022 Alleviating the Inequality of Attention Heads for Neural Machine Translation COLING 2022 A Loss Curvature Perspective on Training Instabilities of Deep Learning Models ICLR 2022 AME: Attention and Memory Enhancement in Hyper-Parameter Optimization CVPR 2022 A Minimal Model for Compositional Generalization on gSCAN EMNLP 2022 Amortized Proximal Optimization NeurIPS 2022 Analyzing and Mitigating Interference in Neural Architecture Search ICML 2022 Analyzing Sharpness along GD Trajectory: Progressive Sharpening and Edge of Stability NeurIPS 2022 A Natural Actor-Critic Framework for Zero-Sum Markov Games ICML 2022 A Neural Pre-Conditioning Active Learning Algorithm to Reduce Label Complexity NeurIPS 2022 A Neural Tangent Kernel Perspective of Infinite Tree Ensembles ICLR 2022 An In-depth Study of Stochastic Backpropagation NeurIPS 2022 An Initial Alignment between Neural Network and Target is Needed for Gradient Descent to Learn ICML 2022 Anticorrelated Noise Injection for Improved Generalization ICML 2022 An Unconstrained Layer-Peeled Perspective on Neural Collapse ICLR 2022 ANVITA-African: A Multilingual Neural Machine Translation System for African Languages EMNLP 2022 A proof of convergence for the gradient descent optimization method with random initializations in the training of neural networks with ReLU activation for piecewise linear target functions JMLR 2022 Are All Linear Regions Created Equal? AISTATS 2022 A Reparametrization-Invariant Sharpness Measure Based on Information Geometry NeurIPS 2022 A Simple Guard for Learned Optimizers ICML 2022 A Simple Hash-Based Early Exiting Approach For Language Understanding and Generation ACL 2022