Beyond Empirical Support: Structured Outlier Generation via Sinkhorn Optimal Transport
stat.ML, cs.LG, math.OC
Submitted: 2026-09-25
Updated: 2026-09-25
Code: https://github.com/hSun08/SBOG
Terminology
Sources
- GenIAS: Generator for Instantiating Anomalies in time Series
- Non-Linear Outlier Synthesis for Out-of-Distribution Detection
- Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy
- BOOD: Boundary-based Out-Of-Distribution Data Generation
- TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis
- TurkerGaze: Crowdsourcing Saliency with Webcam based Eye Tracking
- LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop
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