Paper-Conference

Message Passing-based Inference in Switching Autoregressive Models

The switching autoregressive model is a flexible model for signals generated by non-stationary processes. Unfortunately, evaluation of …

Albert Podusenko, Bart van Erp, Dmitry Bagaev, Bert de Vries

Adaptive importance sampling message passing

The aim of Probabilistic Programming (PP) is to automate inference in probabilistic models. One efficient realization of PP-based …

Semih Akbayrak, İsmail Şenöz, Bert de Vries

Adaptive Optimizer Design for Constrained Variational Inference

This paper addresses the problem of implementing robust and hyperparameter-free natural gradient variational inference. Natural …

Alp Sarı, Semih Akbayrak, İsmail Şenöz, Bert de Vries

Variational message passing for online polynomial NARMAX identification

We propose a variational Bayesian inference procedure for online nonlinear system identification. For each output observation, a set of …

Wouter Kouw, Albert Podusenko, Magnus Koudahl, Maarten Schoukens

ReactiveMP.jl: A Julia package for reactive message passing-based Bayesian inference

ReactiveMP.jl is a native Julia implementation of reactive message passing-based Bayesian inference in probabilistic graphical models …

Dmitry Bagaev, Bert de Vries

Message Passing-Based Inference in the Gamma Mixture Model

The Gamma mixture model is a flexible probability distribution for representing beliefs about scale variables such as precisions. …

Albert Podusenko, Bart van Erp, Dmitry Bagaev, İsmail Şenöz, Bert de Vries

Variational Log-Power Spectral Tracking for Acoustic Signals

This paper proposes a generative hierarchical probabilistic model for acoustic signals where both the frequency decomposition and …

Bart van Erp, İsmail Şenöz, Bert de Vries

The Switching Hierarchical Gaussian Filter

In this paper we discuss variational message passing-based (VMP) inference in a switching Hierarchical Gaussian Filter (HGF). An HGF is …

İsmail Şenöz, Albert Podusenko, Semih Akbayrak, Christoph Mathys, Bert de Vries

Learning Where to Park

We consider active inference as a novel approach to the design of synthetic autonomous agents. In order to assess active inference’s …

Burak, Thijs van de Laar, Magnus Koudahl, Martin Roa-Villescas, Bert de Vries

A Worked Example of Fokker-Planck based Active Inference

The Free Energy Principle (FEP) and its corollary active inference describe a complex theoretical framework with a substantial …

Magnus Koudahl, Bert de Vries