paper-with-me

홈 › Papers

Approximate Bayesian Inference via Bitstring Representations

2025-08-19 · Aleksanteri Sladek, Martin Trapp, Arno Solin arxiv

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 distribution using discrete parameters. We consider both 2D densities and quantized neural networks, where we introduce a tractable learning approach using probabilistic circuits. This method offers a scalable solution to manage complex distributions and provides clear insights into model behavior. We validate our approach with various models, demonstrating inference efficiency without sacrificing accuracy. This work advances scalable, interpretable machine learning by utilizing discrete approximations for probabilistic computations.

📄 PDF Abstract BibTeX arXiv:2508.13598

Code (0)

등록된 구현이 없습니다.

Tasks

Interpretable Machine LearningBayesian Inference

Similar Papers 제목 키워드 기반

Performance Evaluation of Bitstring Representations in a Linear Genetic Programming Framework

2025-11-04 · Clyde Meli, Vitezslav Nezval, Zuzana Kominkova Oplatkova, Victor Buttigieg 외 arxiv

Different bitstring representations can yield varying computational performance. This work compares three bitstring implementations in C++: std::bitset, boost::dynamic_bitset, and a custom direct implementation. Their pe…

Cycle-Consistent Adversarial Learning as Approximate Bayesian Inference

2018-06-05 · Louis C. Tiao, Edwin V. Bonilla, Fabio Ramos

We formalize the problem of learning interdomain correspondences in the absence of paired data as Bayesian inference in a latent variable model (LVM), where one seeks the underlying hidden representations of entities fro…

Bayesian InferenceVariational Inference

DeepMorph: A System for Hiding Bitstrings in Morphable Vector Drawings

2020-11-19 · Søren Rasmussen, Karsten Østergaard Noe, Oliver Gyldenberg Hjermitslev, Henrik Pedersen

We introduce DeepMorph, an information embedding technique for vector drawings. Provided a vector drawing, such as a Scalable Vector Graphics (SVG) file, our method embeds bitstrings in the image by perturbing the drawin…

Camera Pose EstimationDecoderobject-detectionObject Detection+2

Efficient Attack Graph Analysis through Approximate Inference

2016-06-22 · Luis Muñoz-González, Daniele Sgandurra, Andrea Paudice, Emil C. Lupu

Attack graphs provide compact representations of the attack paths that an attacker can follow to compromise network resources by analysing network vulnerabilities and topology. These representations are a powerful tool f…

Bayesian InferenceClustering

Amortized Bayesian inference for clustering models

2018-11-24 · Ari Pakman, Liam Paninski

We develop methods for efficient amortized approximate Bayesian inference over posterior distributions of probabilistic clustering models, such as Dirichlet process mixture models. The approach is based on mapping distri…

Bayesian InferenceClustering