arXiv Analytics

Sign in

arXiv:1810.05500 [cs.LG]AbstractReferencesReviewsResources

Predictive Uncertainty through Quantization

Bastiaan S. Veeling, Rianne van den Berg, Max Welling

Published 2018-10-12Version 1

High-risk domains require reliable confidence estimates from predictive models. Deep latent variable models provide these, but suffer from the rigid variational distributions used for tractable inference, which err on the side of overconfidence. We propose Stochastic Quantized Activation Distributions (SQUAD), which imposes a flexible yet tractable distribution over discretized latent variables. The proposed method is scalable, self-normalizing and sample efficient. We demonstrate that the model fully utilizes the flexible distribution, learns interesting non-linearities, and provides predictive uncertainty of competitive quality.

Related articles: Most relevant | Search more
arXiv:2009.03034 [cs.LG] (Published 2020-09-07)
Ordinal-Content VAE: Isolating Ordinal-Valued Content Factors in Deep Latent Variable Models
arXiv:2308.01731 [cs.LG] (Published 2023-08-03)
Quantification of Predictive Uncertainty via Inference-Time Sampling
arXiv:2308.07209 [cs.LG] (Published 2023-08-14)
Unified Data-Free Compression: Pruning and Quantization without Fine-Tuning