Variational Hierarchical Mixtures for Learning Probabilistic Inverse Dynamics

by   Hany Abdulsamad, et al.

Well-calibrated probabilistic regression models are a crucial learning component in robotics applications as datasets grow rapidly and tasks become more complex. Classical regression models are usually either probabilistic kernel machines with a flexible structure that does not scale gracefully with data or deterministic and vastly scalable automata, albeit with a restrictive parametric form and poor regularization. In this paper, we consider a probabilistic hierarchical modeling paradigm that combines the benefits of both worlds to deliver computationally efficient representations with inherent complexity regularization. The presented approaches are probabilistic interpretations of local regression techniques that approximate nonlinear functions through a set of local linear or polynomial units. Importantly, we rely on principles from Bayesian nonparametrics to formulate flexible models that adapt their complexity to the data and can potentially encompass an infinite number of components. We derive two efficient variational inference techniques to learn these representations and highlight the advantages of hierarchical infinite local regression models, such as dealing with non-smooth functions, mitigating catastrophic forgetting, and enabling parameter sharing and fast predictions. Finally, we validate this approach on a set of large inverse dynamics datasets and test the learned models in real-world control scenarios.


page 5

page 7


A Variational Infinite Mixture for Probabilistic Inverse Dynamics Learning

Probabilistic regression techniques in control and robotics applications...

Variational Imbalanced Regression

Existing regression models tend to fall short in both accuracy and uncer...

Influential Observations in Bayesian Regression Tree Models

BCART (Bayesian Classification and Regression Trees) and BART (Bayesian ...

A Gentle Introduction to Bayesian Hierarchical Linear Regression Models

Considering the flexibility and applicability of Bayesian modeling, in t...

Variational EP with Probabilistic Backpropagation for Bayesian Neural Networks

I propose a novel approach for nonlinear Logistic regression using a two...

Finding the Perfect Fit: Applying Regression Models to ClimateBench v1.0

Climate projections using data driven machine learning models acting as ...

Locally Weighted Regression with different Kernel Smoothers for Software Effort Estimation

Estimating software effort has been a largely unsolved problem for decad...

Please sign up or login with your details

Forgot password? Click here to reset