Optimization & Theory

Discriminative Feature Attributions: Bridging Post Hoc Explainability and Inherent Interpretability NeurIPS 2023 Discriminator-Cooperated Feature Map Distillation for GAN Compression CVPR 2023 Disentangling the Mechanisms Behind Implicit Regularization in SGD ICLR 2023 Dissecting the Effects of SGD Noise in Distinct Regimes of Deep Learning ICML 2023 Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes ACL 2023 Distill or Annotate? Cost-Efficient Fine-Tuning of Compact Models ACL 2023 DistilPose: Tokenized Pose Regression With Heatmap Distillation CVPR 2023 DIVISION: Memory Efficient Training via Dual Activation Precision ICML 2023 DMIS: Dynamic Mesh-Based Importance Sampling for Training Physics-Informed Neural Networks AAAI 2023 Does Deep Learning Learn to Abstract? A Systematic Probing Framework ICLR 2023 DoG is SGD’s Best Friend: A Parameter-Free Dynamic Step Size Schedule ICML 2023 Do Not Train It: A Linear Neural Architecture Search of Graph Neural Networks ICML 2023 DropMessage: Unifying Random Dropping for Graph Neural Networks AAAI 2023 Dropout Reduces Underfitting ICML 2023 Dropout Training is Distributionally Robust Optimal JMLR 2023 DSEE: Dually Sparsity-embedded Efficient Tuning of Pre-trained Language Models ACL 2023 Dual Focal Loss for Calibration ICML 2023 Dynamic Low-rank Estimation for Transformer-based Language Models EMNLP 2023 Dynamic Regularized Sharpness Aware Minimization in Federated Learning: Approaching Global Consistency and Smooth Landscape ICML 2023 Dynamic Stashing Quantization for Efficient Transformer Training EMNLP 2023 Dynamic Structure Pruning for Compressing CNNs AAAI 2023 Dynamic Token Pruning in Plain Vision Transformers for Semantic Segmentation ICCV 2023 Easy to Decide, Hard to Agree: Reducing Disagreements Between Saliency Methods ACL 2023 Ecosystem-level Analysis of Deployed Machine Learning Reveals Homogeneous Outcomes NeurIPS 2023 EffConv: Efficient Learning of Kernel Sizes for Convolution Layers of CNNs AAAI 2023