Timezone: »
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.
Author Information
Marco Lorenzi (Inria Sophia Antipolis)
Maurizio Filippone (Eurecom)
Related Events (a corresponding poster, oral, or spotlight)
-
2018 Oral: Constraining the Dynamics of Deep Probabilistic Models »
Thu Jul 12th 09:20 -- 09:40 AM Room A4
More from the Same Authors
-
2019 Poster: Good Initializations of Variational Bayes for Deep Models »
Simone Rossi · Pietro Michiardi · Maurizio Filippone -
2019 Oral: Good Initializations of Variational Bayes for Deep Models »
Simone Rossi · Pietro Michiardi · Maurizio Filippone -
2019 Poster: Sparse Multi-Channel Variational Autoencoder for the Joint Analysis of Heterogeneous Data »
Luigi Antelmi · Nicholas Ayache · Philippe Robert · Marco Lorenzi -
2019 Oral: Sparse Multi-Channel Variational Autoencoder for the Joint Analysis of Heterogeneous Data »
Luigi Antelmi · Nicholas Ayache · Philippe Robert · Marco Lorenzi -
2017 Poster: Random Feature Expansions for Deep Gaussian Processes »
Kurt Cutajar · Edwin Bonilla · Pietro Michiardi · Maurizio Filippone -
2017 Talk: Random Feature Expansions for Deep Gaussian Processes »
Kurt Cutajar · Edwin Bonilla · Pietro Michiardi · Maurizio Filippone