arXiv Statistics ML
Beyond Empirical Support: Structured Outlier Generation via Sinkhorn Optimal Transport
Read the original on arXiv Statistics ML →The Flow has not summarised this story yet — read it at arXiv Statistics ML.
Related stories
arXiv Machine Learning
Sep 24
CAST: Context- and Anomaly Structure-Conditioned Time Series Anomaly Generation
CAST is a framework for generating anomalous time series that addresses the scarcity and heterogeneity of anomaly data. It uses a two‑stage approach: pretraining on abundant normal data to learn system dynamics, then finetuning with anomaly structure representations to capture diverse anomaly morphologies. Experiments on real‑world datasets show that CAST outperforms existing methods in both generation quality and downstream task performance.
arXiv Machine Learning
Aug 14
Wasserstein Filtering: A Sample Selection Method for Robust Distribution Learning
arXiv:2608. 13418v1 Announce Type: cross Abstract: Given a dataset where a portion of the samples are contaminated, our goal is to recover the underlying clean population distribution.
Hugging Face Trending Papers
Aug 13
Wasserstein Filtering: A Sample Selection Method for Robust Distribution Learning
Given a dataset where a portion of the samples are contaminated, our goal is to recover the underlying clean population distribution. To this end, we propose Wasserstein Filtering (WF), a novel sample selection framework that discards a fraction of suspicious samples and estimates the target distribution using the empirical measure of the remaining data.
arXiv Machine Learning
Jun 9
Anomaly-Preference Image Generation
arXiv:2605. 02439v3 Announce Type: replace-cross Abstract: Synthesizing realistic and diverse anomalous samples from limited data is vital for robust model generalization.
arXiv Machine Learning
Sep 11
Optimizing Three Critical Factors for Practical and Effective OOD Detection Fine-Tuning
The paper introduces a framework for out-of-distribution (OOD) detection that addresses the trade‑off between detection performance and classification accuracy caused by fine‑tuning with auxiliary outlier data. It optimizes three factors—model reminder, data sampling, and representation learning—by proposing Self‑Knowledge Distillation to preserve accuracy, Semi‑hard Outlier Sampling to enhance detection with minimal data, and Outlier‑aware Supervised Contrastive Learning to improve ID‑OOD separability. The combined approach yields cumulative gains, outperforming existing methods on diverse benchmarks, especially in long‑tailed scenarios, and offers a robust baseline for real‑world OOD detection.
arXiv AI
Jul 17
VAN-AD: Visual Masked Autoencoder with Normalizing Flow For Time Series Anomaly Detection
arXiv:2603. 26842v3 Announce Type: replace-cross Abstract: Time series anomaly detection (TSAD) is essential for maintaining the reliability and security of IoT-enabled service systems.