Skip to Main content Skip to Navigation
Conference papers

Constraining the Dynamics of Deep Probabilistic Models

Abstract : We introduce a novel generative formulation of deep probabilistic models implementing "soft" constraints on their function dynamics. In particular, we develop a flexible methodological framework where the modeled functions and derivatives of a given order are subject to inequality or equality constraints. We then characterize the posterior distribution over model and constraint parameters through stochastic variational inference. As a result, the proposed approach allows for accurate and scalable uncertainty quantification on the predictions and on all parameters. We demonstrate the application of equality constraints in the challenging problem of parameter inference in ordinary differential equation models, while we showcase the application of inequality constraints on the problem of monotonic regression of count data. The proposed approach is extensively tested in several experimental settings, leading to highly competitive results in challenging modeling applications, while offering high expressiveness, flexibility and scalability.
Complete list of metadata
Contributor : Marco Lorenzi Connect in order to contact the contributor
Submitted on : Wednesday, July 18, 2018 - 1:51:54 PM
Last modification on : Saturday, June 25, 2022 - 11:31:40 PM

Links full text


  • HAL Id : hal-01843006, version 1
  • ARXIV : 1802.05680


Marco Lorenzi, Maurizio Filippone. Constraining the Dynamics of Deep Probabilistic Models. ICML 2018 - The 35th International Conference on Machine Learning, Jul 2018, Stockholm, Sweden. pp.3233-3242. ⟨hal-01843006⟩



Record views