Optimization & Theory

Convergence of Proximal Point and Extragradient-Based Methods Beyond Monotonicity: the Case of Negative Comonotonicity ICML 2023 Coop: Memory is not a Commodity NeurIPS 2023 CoordFill: Efficient High-Resolution Image Inpainting via Parameterized Coordinate Querying AAAI 2023 CORNN: Convex optimization of recurrent neural networks for rapid inference of neural dynamics NeurIPS 2023 Correlation Loss: Enforcing Correlation between Classification and Localization AAAI 2023 Co-Training 2L Submodels for Visual Recognition CVPR 2023 Co-training and Co-distillation for Quality Improvement and Compression of Language Models EMNLP 2023 COT: Unsupervised Domain Adaptation With Clustering and Optimal Transport CVPR 2023 CowClip: Reducing CTR Prediction Model Training Time from 12 Hours to 10 Minutes on 1 GPU AAAI 2023 CP3: Channel Pruning Plug-In for Point-Based Networks CVPR 2023 CReTIHC: Designing Causal Reasoning Tasks about Temporal Interventions and Hallucinated Confoundings EMNLP 2023 Critical Initialization of Wide and Deep Neural Networks using Partial Jacobians: General Theory and Applications NeurIPS 2023 Cross-Modal Attribute Insertions for Assessing the Robustness of Vision-and-Language Learning ACL 2023 CSTAR: Towards Compact and Structured Deep Neural Networks with Adversarial Robustness AAAI 2023 Curvature-Balanced Feature Manifold Learning for Long-Tailed Classification CVPR 2023 D4FT: A Deep Learning Approach to Kohn-Sham Density Functional Theory ICLR 2023 DamoFD: Digging into Backbone Design on Face Detection ICLR 2023 Dataset Distillation with Convexified Implicit Gradients ICML 2023 DeAR: A Deep-Learning-Based Audio Re-recording Resilient Watermarking AAAI 2023 Decentralized Learning: Theoretical Optimality and Practical Improvements JMLR 2023 Decentralized SGD and Average-direction SAM are Asymptotically Equivalent ICML 2023 Decomposed Prompt Tuning via Low-Rank Reparameterization EMNLP 2023 Deconstructing Data Reconstruction: Multiclass, Weight Decay and General Losses NeurIPS 2023 Deep Declarative Dynamic Time Warping for End-to-End Learning of Alignment Paths ICLR 2023 Deep Dive Into Gradients: Better Optimization for 3D Object Detection With Gradient-Corrected IoU Supervision CVPR 2023