Research
Mitigating the Likelihood Paradox in Flow-based OOD Detection: An Entropic Perspective
arXiv:2602.09581v2 Announce Type: replace-cross Abstract: Deep generative models that can tractably compute input likelihoods, including normalizing flows, often assign unexpectedly high likelihoods t
arXiv:2602.09581v2 Announce Type: replace-cross Abstract: Deep generative models that can tractably compute input likelihoods, including normalizing flows, often assign unexpectedly high likelihoods to out-of-distribution (OOD) inputs. We mitigate this paradox from an entropic perspective with Semantic Proportional Entropy Manipulation (SPEM), a training-free procedure that applies stronger perturbations to inputs less similar to an in-distribution (ID) memory bank. We derive theoretical lower bounds showing that this entropy gap increases the expected log-likelihood difference in favor of the ID, and experiments on standard benchmarks show that this manipulation realigns the likelihood ordering with human intuition. Strikingly, this realignment persists even when the flow is given only visually meaningless noise instead of the original input, and we analyze this phenomenon theoretically to characterize the conditions under which it occurs.
Related
- Why Does Counterintuitive Likelihood Behavior Rarely Emerge in Tabular Anomaly Detection?
- Iterative Flow Matching: Path Correction and Gradual Refinement for Enhanced Generative Modeling
- Joint Distillation for Fast Likelihood Evaluation and Sampling in Flow-based Models
Source: arXiv cs.AI | 2026-10-26