Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Bert de Vries

Bert de Vries

3 indexed papers

Recent (6 mo)
3
With code
0
Influential cites
0
Benchmarked
0

Publications per year

3
26

Top categories

AI×2Stats Theory×1Info Theory×1Category Theory×1Probability×1ML×1

Frequent co-authors

Thijs van de Laar2×
Mykola Lukashchuk2×
Raphaël Trésor1×
Wouter W. L. Nuijten1×
Kyrylo Yemets1×
Wouter M. Kouw1×

Research Timeline

2026
Composing Non-Conjugate Factor Graphs with Closed-Form Variational Inference

The paper introduces a framework for composing deep probabilistic models using five specific factor-graph primitives that guarantee closed-form variational inference, thereby preserving tractability in complex architectures.

What Type of Inference is Active Inference?

This paper provides a detailed message-passing scheme for EFE-based planning and clarifies the corrections needed for cross-entropy planning and full EFE-based planning.

Reformulation Invariance and the Axiomatic Foundations of Inference

This paper argues that the choice of divergence in statistical inference can be justified by requiring invariance to problem reformulations, leading to the selection of the Kullback-Leibler divergence.

Highlighted terms show continued research focus across papers

Papers

math.STcs.ITmath.CTTheoreticalRecentJun 19, 2026

Reformulation Invariance and the Axiomatic Foundations of Inference

Raphaël Trésor, Thijs van de Laar, Bert de Vries

This paper argues that the choice of divergence in statistical inference can be justified by requiring invariance to problem reformulations, leading to the selection of the Kullback-Leibler divergence…

View →
cs.AIRecent
Jun 3, 2026

What Type of Inference is Active Inference?

Wouter W. L. Nuijten, Mykola Lukashchuk, Thijs van de Laar, Bert de Vries

This paper provides a detailed message-passing scheme for EFE-based planning and clarifies the corrections needed for cross-entropy planning and full EFE-based planning.

View →
cs.LGcs.AIRecentMay 28, 2026

Composing Non-Conjugate Factor Graphs with Closed-Form Variational Inference

Mykola Lukashchuk, Kyrylo Yemets, Wouter M. Kouw, Dmitry Bagaev +3 more

The paper introduces a framework for composing deep probabilistic models using five specific factor-graph primitives that guarantee closed-form variational inference, thereby preserving tractability i…

View →