Multi-Marginal Inverse Optimal Transport for Contrastive Learning Via Explicit Anchor-Positive-Negative Coupling
stat.ML, cs.LG
Submitted: 2026-09-27
Updated: 2026-09-27
Terminology
Sources
- On Mutual Information Maximization for Representation Learning
- PROTOCOL: Partial Optimal Transport-enhanced Contrastive Learning for Imbalanced Multi-view Clustering
- Contrasting Multiple Representations with the Multi-Marginal Matching Gap
- VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning
- Towards understanding neural collapse in supervised contrastive learning with the information bottleneck method
- Symmetric Neural-Collapse Representations with Supervised Contrastive Loss: The Impact of ReLU and Batching
- Global Minimizers of Sigmoid Contrastive Loss
- Understanding Self-Supervised Learning via Gaussian Mixture Models
- A Statistical Theory of Contrastive Pre-training and Multimodal Generative AI
- A Generalization Theory for Zero-Shot Prediction
Related papers
- Behavior of prediction performance metrics with rare events
- Optimal Estimation of Generic Dynamics by Path-Dependent Neural Jump ODEs
- A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors
- One Permutation Is All You Need: Fast, Deterministic Feature Importance and Model Stress-Testing
- Online Conformal Prediction for Non-Exchangeable Panel Data
- Deep Time-Series Forecasting in 10 Years: A Survey