Inference, Fast and Slow: Reinterpreting VAEs for OOD Detection
Keywords: unsupervised, outlier detection, ood, out-of-distribution, anomaly detection, variational autoencoder, VAE
TL;DR: We show that by leveraging sufficient statistics derived from the likelihood path (LPath) of VAEs, our the LPath method can achieve SOTA performance for unsupervised, one sample OOD detection.
Abstract: lthough likelihood-based methods are theoretically appealing, deep generative models (DGMs) often produce unreliable likelihood estimates in practice, particu larly for out-of-distribution (OOD) detection. We reinterpret variational autoen coders (VAEs) through the lens of fast and slow weights. Our approach is guided by the proposed Likelihood Path (LPath) Principle, which extends the classical likelihood principle. A critical decision in our method is the selection of statistics for classical density estimation algorithms. The sweet spot should contain just enough information that’s sufficient for OOD detection but not too much to suffer from the curse of dimensionality. Our LPath principle achieves this by selecting the sufficient statistics that form the "path" toward the likelihood. We demonstrate that this likelihood path leads to SOTA OOD detection performance, even when the likelihood itself is unreliable.
Primary Area: unsupervised, self-supervised, semi-supervised, and supervised representation learning
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 13255
Loading