training dynamics

Towards Lossless Dataset Distillation via Difficulty-Aligned Trajectory Matching ICLR 2024 Towards the Dynamics of a DNN Learning Symbolic Interactions NeurIPS 2024 Training Dynamics of Multi-Head Softmax Attention for In-Context Learning: Emergence, Convergence, and Optimality (extended abstract) COLT 2024 Training Dynamics of Transformers to Recognize Word Co-occurrence via Gradient Flow Analysis NeurIPS 2024 Transformer verbatim in-context retrieval across time and scale CoNLL 2024 Understanding Surprising Generalization Phenomena in Deep Learning AAAI 2024 Understanding the Generalization Benefits of Late Learning Rate Decay AISTATS 2024 Unveil Benign Overfitting for Transformer in Vision: Training Dynamics, Convergence, and Generalization NeurIPS 2024 Unveiling the Role of Pretraining in Direct Speech Translation EMNLP 2024 What is Dataset Distillation Learning? ICML 2024 Why Do We Need Weight Decay in Modern Deep Learning? NeurIPS 2024 Bifurcations and loss jumps in RNN training NeurIPS 2023 Does Continual Learning Equally Forget All Parameters? ICML 2023 Is This Loss Informative? Faster Text-to-Image Customization by Tracking Objective Dynamics NeurIPS 2023 Learning from Training Dynamics: Identifying Mislabeled Data beyond Manually Designed Features AAAI 2023 Memorisation Cartography: Mapping out the Memorisation-Generalisation Continuum in Neural Machine Translation EMNLP 2023 Metadata Archaeology: Unearthing Data Subsets by Leveraging Training Dynamics ICLR 2023 NTK-SAP: Improving neural network pruning by aligning training dynamics ICLR 2023 On the Training Instability of Shuffling SGD with Batch Normalization ICML 2023 Phase diagram of early training dynamics in deep neural networks: effect of the learning rate, depth, and width NeurIPS 2023 Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling ICML 2023 QADYNAMICS: Training Dynamics-Driven Synthetic QA Diagnostic for Zero-Shot Commonsense Question Answering EMNLP 2023 Scan and Snap: Understanding Training Dynamics and Token Composition in 1-layer Transformer NeurIPS 2023 Spectral Evolution and Invariance in Linear-width Neural Networks NeurIPS 2023 TiDAL: Learning Training Dynamics for Active Learning ICCV 2023