Neural Network Optimization

Extended Unconstrained Features Model for Exploring Deep Neural Collapse ICML 2022 Extrapolation and Spectral Bias of Neural Nets with Hadamard Product: a Polynomial Net Study NeurIPS 2022 Fast and Efficient Restoration of Extremely Dark Light Fields WACV 2022 Fast and Robust Online Inference with Stochastic Gradient Descent via Random Scaling AAAI 2022 Fast Convex Optimization for Two-Layer ReLU Networks: Equivalent Model Classes and Cone Decompositions ICML 2022 Faster non-convex federated learning via global and local momentum UAI 2022 Faster Single-loop Algorithms for Minimax Optimization without Strong Concavity AISTATS 2022 Fast Finite Width Neural Tangent Kernel ICML 2022 Fast Mixing of Stochastic Gradient Descent with Normalization and Weight Decay NeurIPS 2022 Feedback Gradient Descent: Efficient and Stable Optimization with Orthogonality for DNNs AAAI 2022 Finding Dynamics Preserving Adversarial Winning Tickets AISTATS 2022 Finding the Dominant Winning Ticket in Pre-Trained Language Models ACL 2022 Fine-Tuning Pre-trained Transformers into Decaying Fast Weights EMNLP 2022 Finite-Time Analysis of Adaptive Temporal Difference Learning with Deep Neural Networks NeurIPS 2022 Fire Together Wire Together: A Dynamic Pruning Approach With Self-Supervised Mask Prediction CVPR 2022 Fisher SAM: Information Geometry and Sharpness Aware Minimisation ICML 2022 Forecasting Asset Dependencies to Reduce Portfolio Risk AAAI 2022 Fortuitous Forgetting in Connectionist Networks ICLR 2022 FPT: Improving Prompt Tuning Efficiency via Progressive Training EMNLP 2022 Fractional Adaptive Linear Units AAAI 2022 Frequency Dynamic Convolution: Frequency-Adaptive Pattern Recognition for Sound Event Detection Interspeech 2022 From Gradient Flow on Population Loss to Learning with Stochastic Gradient Descent NeurIPS 2022 GA-SAM: Gradient-Strength based Adaptive Sharpness-Aware Minimization for Improved Generalization EMNLP 2022 Generalization Bounds for Gradient Methods via Discrete and Continuous Prior NeurIPS 2022 Generalization Bounds using Lower Tail Exponents in Stochastic Optimizers ICML 2022