Characteristic Circuit
Dec 10, 2023
Speakers
Zhongjie Yu
Speaker · 0 followers
Martin Trapp
Speaker · 0 followers
Kristian Kersting
Speaker · 0 followers
About
In many real-world scenarios it is crucial to be able to reliably and efficiently reason under uncertainty while capturing complex relationships in data. Probabilistic circuits (PCs), a prominent family of tractable probabilistic models, offer a remedy to this challenge by composing simple, tractable distributions into a high-dimensional probability distribution. However, learning PCs on heterogeneous data is challenging and densities of some parametric distributions are not available in closed form, limiting their potential use. We introduce characteristic circuits (CCs), a family of tractable probabilistic models providing a unified formalization of distributions over heterogeneous data in the spectral domain. The one-to-one relationship between characteristic functions and probability measures enables us to learn high-dimensional distributions on heterogeneous data domains and facilitates efficient probabilistic inference even when no closed-form density function is available. We show that the structure and parameters of CCs can be learned efficiently from the data and find that CCs outperform state-of-the-art density estimators for heterogeneous data domains on common benchmark data sets.In many real-world scenarios it is crucial to be able to reliably and efficiently reason under uncertainty while capturing complex relationships in data. Probabilistic circuits (PCs), a prominent family of tractable probabilistic models, offer a remedy to this challenge by composing simple, tractable distributions into a high-dimensional probability distribution. However, learning PCs on heterogeneous data is challenging and densities of some parametric distributions are not available in closed…
Organizer
NeurIPS 2023
Account · 651 followers
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Causal normalizing flows: from theory to practice
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
T2I-CompBench: A Comprehensive Benchmark for Open-world Compositional Text-to-image Generation
Watch later
Kaiyi Huang, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
DeepPCR: Parallelizing Sequential Operations in Neural Networks
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Estimating Uncertainty in Multimodal Foundation Models using Public Internet Data
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Are Emergent Abilities of Large Language Models a Mirage?
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
On the Robustness of Removal-Based Feature Attributions
Watch later
Chris Lin, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%