Neural Network Optimization

Dissecting the Effects of SGD Noise in Distinct Regimes of Deep Learning ICML 2023 DisWOT: Student Architecture Search for Distillation WithOut Training CVPR 2023 Does Continual Learning Equally Forget All Parameters? ICML 2023 DoG is SGD’s Best Friend: A Parameter-Free Dynamic Step Size Schedule ICML 2023 Domain Generalization Guided by Gradient Signal to Noise Ratio of Parameters ICCV 2023 Don't be so Monotone: Relaxing Stochastic Line Search in Over-Parameterized Models NeurIPS 2023 Don’t blame Dataset Shift! Shortcut Learning due to Gradients and Cross Entropy NeurIPS 2023 Don’t Predict Counterfactual Values, Predict Expected Values Instead AAAI 2023 DoWG Unleashed: An Efficient Universal Parameter-Free Gradient Descent Method NeurIPS 2023 DRGCN: Dynamic Evolving Initial Residual for Deep Graph Convolutional Networks AAAI 2023 DropIT: Dropping Intermediate Tensors for Memory-Efficient DNN Training ICLR 2023 DSGD-CECA: Decentralized SGD with Communication-Optimal Exact Consensus Algorithm ICML 2023 DualVC: Dual-mode Voice Conversion using Intra-model Knowledge Distillation and Hybrid Predictive Coding Interspeech 2023 Dynamic Neural Network for Multi-Task Learning Searching Across Diverse Network Topologies CVPR 2023 Dynamic Regularized Sharpness Aware Minimization in Federated Learning: Approaching Global Consistency and Smooth Landscape ICML 2023 Dynamics of Finite Width Kernel and Prediction Fluctuations in Mean Field Neural Networks NeurIPS 2023 Dynamic Tensor Decomposition via Neural Diffusion-Reaction Processes NeurIPS 2023 Early Exit with Disentangled Representation and Equiangular Tight Frame ACL 2023 EffConv: Efficient Learning of Kernel Sizes for Convolution Layers of CNNs AAAI 2023 Efficient CTC Regularization via Coarse Labels for End-to-End Speech Translation EACL 2023 Efficient Hyper-parameter Optimization with Cubic Regularization NeurIPS 2023 Efficient Uncertainty Quantification and Reduction for Over-Parameterized Neural Networks NeurIPS 2023 EICIL: Joint Excitatory Inhibitory Cycle Iteration Learning for Deep Spiking Neural Networks NeurIPS 2023 End-to-End Learning for Stochastic Optimization: A Bayesian Perspective ICML 2023 Enhanced Training of Query-Based Object Detection via Selective Query Recollection CVPR 2023