Martin Trapp — accepted AI-conference papers

2026

Position: Agentic AI systems should be making Bayes-consistent decisions

Theodore Papamarkou, Pierre Alquier, Matthias Bauer, Wray Buntine, Andrew Davison, Gintare Karolina Dziugaite +24

ICML 2026poster

LLMs excel at predictive tasks and complex reasoning tasks, but many high-value deployments rely on decisions under uncertainty, for example, which tool to call, which expert to consult, or how many resources to invest. While the usefulness and feasibility of Bayesian approaches remain unclear for L…

Cited by 0 Source ↗Scholar ↗

2026

Post-hoc Probabilistic Vision-Language Models

Anton Baumann, Rui Li, Marcus Klasson, Santeri Mentu, Shyamgopal Karthik, Zeynep Akata +2

ICLR 2026poster

Vision-language models (VLMs), such as CLIP and SigLIP, have found remarkable success in classification, retrieval, and generative tasks. For this, VLMs deterministically map images and text descriptions to a joint latent space in which their similarity is assessed using the cosine similarity. Howev…

Cited by 0 Source ↗code ↗Scholar ↗

2025

Approximate Bayesian Inference via Bitstring Representations

Aleksanteri Sladek, Martin Trapp, Arno Solin

UAI 2025

The machine learning community has recently put effort into quantized or low-precision arithmetics to scale large models. This paper proposes performing probabilistic inference in the quantized, discrete parameter space created by these representations, effectively enabling us to learn a continuous

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2025

Streamlining Prediction in Bayesian Deep Learning

Rui Li, Marcus Klasson, Arno Solin, Martin Trapp

ICLR 2025poster

The rising interest in Bayesian deep learning (BDL) has led to a plethora of methods for estimating the posterior distribution. However, efficient computation of inferences, such as predictions, has been largely overlooked with Monte Carlo integration remaining the standard. In this work we examine…

Cited by 2 Source ↗PDF ↗code ↗Scholar ↗

2024

On Hardware-efficient Inference in Probabilistic Circuits

Lingyun Yao, Martin Trapp, Jelin Leslin, Gaurav Singh, Peng Zhang, Karthekeyan Periasamy +1

UAI 2024poster

Probabilistic circuits (PCs) offer a promising avenue to perform embedded reasoning under uncertainty. They support efficient and exact computation of various probabilistic inference tasks by design. Hence, hardware-efficient computation of PCs is highly interesting for edge computing applications.…

Cited by 0 Source ↗PDF ↗Scholar ↗

2024

Subtractive Mixture Models via Squaring: Representation and Learning

Lorenzo Loconte, Aleksanteri Mikulus Sladek, Stefan Mengel, Martin Trapp, Arno Solin, Nicolas Gillis +1

ICLR 2024spotlight

Mixture models are traditionally represented and learned by adding several distributions as components. Allowing mixtures to subtract probability mass or density can drastically reduce the number of components needed to model complex distributions. However, learning such subtractive mixtures while e…

Cited by 18 Source ↗PDF ↗Scholar ↗

2023

Characteristic Circuits

Zhongjie Yu, Martin Trapp, Kristian Kersting

NeurIPS 2023oral

In many real-world scenarios it is crucial to be able to reliably and efficiently reason under uncertainty while capturing complex relationships in data. Probabilistic circuits (PCs), a prominent family of tractable probabilistic models, offer a remedy to this challenge by composing simple, tracta…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2022

Uncertainty-Guided Source-Free Domain Adaptation

Subhankar Roy, Martin Trapp, Andrea Pilzer, Juho Kannala, Nicu Sebe, Elisa Ricci +1

ECCV 2022poster

"Source-free domain adaptation (SFDA) aims to adapt a classifier to an unlabelled target data set by only using a pre-trained source model. However, the absence of the source data and the domain shift makes the predictions on the target data unreliable. We propose quantifying the uncertainty in the…

Cited by 90 Source ↗PDF ↗code ↗Scholar ↗

2021

Leveraging probabilistic circuits for nonparametric multi-output regression

Zhongjie Yu, Mingye Zhu, Martin Trapp, Arseny Skryagin, Kristian Kersting

UAI 2021poster

Inspired by recent advances in the field of expert-based approximations of Gaussian processes (GPs), we present an expert-based approach to large-scale multi-output regression using single-output GP experts. Employing a deeply structured mixture of single-output GPs encoded via a probabilistic circu…

Cited by 16 Source ↗PDF ↗code ↗Scholar ↗

2021

Periodic Activation Functions Induce Stationarity

Lassi Meronen, Martin Trapp, Arno Solin

NeurIPS 2021poster

Neural network models are known to reinforce hidden data biases, making them unreliable and difficult to interpret. We seek to build models that `know what they do not know' by introducing inductive biases in the function space. We show that periodic activation functions in Bayesian neural networks…

Cited by 30 Source ↗PDF ↗code ↗Scholar ↗

2020

Deep Structured Mixtures of Gaussian Processes

Martin Trapp, Robert Peharz, Franz Pernkopf, Carl Edward Rasmussen

AISTATS 2020poster

Gaussian Processes (GPs) are powerful non-parametric Bayesian regression models that allow exact posterior inference, but exhibit high computational and memory costs. In order to improve scalability of GPs, approximate posterior inference is frequently employed, where a prominent class of approximat…

Cited by 43 Source ↗PDF ↗code ↗Scholar ↗

2020

Einsum Networks: Fast and Scalable Learning of Tractable Probabilistic Circuits

Robert Peharz, Steven Lang, Antonio Vergari, Karl Stelzner, Alejandro Molina, Martin Trapp +3

ICML 2020poster

Probabilistic circuits (PCs) are a promising avenue for probabilistic modeling, as they permit a wide range of exact and efficient inference routines. Recent “deep-learning-style” implementations of PCs strive for a better scalability, but are still difficult to train on real-world data, due to thei…

Cited by 144 Source ↗PDF ↗code ↗Scholar ↗

2019

Bayesian Learning of Sum-Product Networks

Martin Trapp, Robert Peharz, Hong Ge, Franz Pernkopf, Zoubin Ghahramani

NeurIPS 2019poster

Sum-product networks (SPNs) are flexible density estimators and have received significant attention due to their attractive inference properties. While parameter learning in SPNs is well developed, structure learning leaves something to be desired: Even though there is a plethora of SPN structure le…

Cited by 61 Source ↗PDF ↗code ↗Scholar ↗

2019

Random Sum-Product Networks: A Simple and Effective Approach to Probabilistic Deep Learning

Robert Peharz, Antonio Vergari, Karl Stelzner, Alejandro Molina, Xiaoting Shao, Martin Trapp +2

UAI 2019poster

Sum-product networks (SPNs) are expressive probabilistic models with a rich set of exact and efficient inference routines. However, in order to guarantee exact inference, they require specific structural constraints, which complicate learning SPNs from data. Thereby, most SPN structure learners prop…

Cited by 142 Source ↗PDF ↗code ↗Scholar ↗