Latest Bayesian Deep Learning Research Papers

The newest Bayesian Deep Learning papers from across the field — arXiv, NeurIPS, CVPR, Nature, and more — refreshed daily and ranked by relevance. Distill AI tracks Bayesian Deep Learning so you don’t have to: get the standout work delivered to your inbox every morning, with 2-sentence summaries and the option to chat with any paper.

Recent papers

• Cautious optimism for deep parameterized quantum circuits
  Marie Kempkes, Elies Gil-Fuster, Carlos Bravo-Prieto, Aroosa Ijaz et al. · arXiv · Jul 23, 2026

  A central challenge in quantum machine learning is understanding the scaling behavior of parameterized quantum circuits (PQCs). In particular, it remains unclear how their performance on unseen data changes as the number of trainable parame…

• Transformer-based Diffusion models for Hydrological Time Series Probabilistic Imputation and Forecasting
  Ferdinand Bhavsar, Lionel Benoit, Maxime Savatier, Edith Gabriel · arXiv · Jul 23, 2026

  The modeling of hydrometeorological time series with limited observations is a key challenge in the monitoring of hydro-systems and water resources, as well as for flood or drought risk assessment. Due to the high variability of the underly…

• Automatic knot selection in smooth additive models
  Nicolás Carrizosa, Vanesa Guerrero, María Durbán · arXiv · Jul 23, 2026

  B-spline regression constitutes a widely used framework for nonparametric modeling. The performance of this methodology depends on specifying the number and placement of changepoints, known as knots, prior to the estimation process. Such kn…

• Factorized neural posterior estimation for rapid and reliable inference of parameterized post-Einsteinian deviation parameters in gravitational waves
  Xin Zhang, Y Zhang, Tian-Yang Sun, Yue Wang et al. · Communications in Theoretic... · Jul 23, 2026

  Abstract The direct detection of gravitational waves (GWs) by LIGO has strikingly confirmed general relativity (GR), but testing GR via GWs requires estimating parameterized post-Einsteinian (ppE) deviation parameters in waveform models. Tr…

• Adaptive Bayesian Online Learning via Expert Aggregation
  Jungbin Jun, Ilsang Ohn · arXiv · Jul 22, 2026

  Bayesian online learning promises uncertainty-aware prediction on data streams, but its performance hinges on inferential choices, including learning rates, prior distributions and variational families, which are usually fixed before seeing…

• SPECTRA: State-Space Exogenous Context and Temporal-Frequency Resolution Architecture for Probabilistic Energy Forecasting
  Hang Ye, Xinyan Jiang, Yuedong Shi, Yangxin Zhu et al. · arXiv · Jul 22, 2026

  Modern power systems increasingly require probabilistic forecasts amid interacting uncertainties from renewable intermittency, flexible demand, market volatility, and weather-dependent generation. However, existing methods often treat multi…

• Exploring self-supervised deep sparse autoencoders for robust feature selection in radiomics analysis
  Sithin Thulasi Seetha, A. Messina, Alessandra Casale, Enrico Garanzini et al. · Scientific Reports · Jul 22, 2026

  While considerable effort has been devoted to examining how variations in study protocols, acquisition settings, and annotations influence radiomics features, the role of feature selection (FS) methods largely remains unexplored. This study…

• Academic Performance Forecasting via Data Imputation and Bayesian Neural Networks
  Yutaka Yamada, Koshi Watanabe, Keisuke Maeda, Takahiro Ogawa et al. · Applied Sciences · Jul 22, 2026

  This study aims to accurately predict students’ academic performance trajectories for university entrance examinations by proposing a machine learning framework that explicitly accounts for missing data and uncertainty. Mock examination dat…

• A Bayesian Framework for Built-in Input Dimension Reduction for Gaussian Process Modeling
  Eric Herrison Gyamfi, Emily L. Kang, Bledar A. Konomi, Guang Lin · arXiv · Jul 21, 2026

  Gaussian process (GP) modeling is widely used in computational science and engineering. However, fitting a GP to high-dimensional inputs remains challenging due to the curse of dimensionality. While various methods have been proposed to red…

• Strong Gravitational Lensing Posterior Sampling in Pixel-Space Using Diffusion Models and Recurrent Inference Machines
  Guillaume Payeur, Laurence Perreault-Levasseur, Gabriel Missael Barco, Yashar Hezaveh · arXiv · Jul 21, 2026

  Modeling galaxy-galaxy strong gravitational lenses to infer the brightness of the source galaxy and the mass distribution of the foreground galaxy is computationally challenging, particularly for high-resolution, high signal-to-noise ratio …

• Provable diffusion-based posterior sampling for linear inverse problems via DDIM
  Yuchen Jiao, Na Li, Changxiao Cai, Yuxin Chen et al. · arXiv · Jul 21, 2026

  Diffusion-based methods have achieved remarkable empirical success in solving inverse problems. However, many existing posterior samplers either lack rigorous theoretical guarantees or incur substantial computational overhead. We propose a …

• Some cautionary tales about Bayesian predictive inference
  Emanuela Dreassi, Fabrizio Leisen, Luca Pratelli, Pietro Rigo · arXiv · Jul 21, 2026

  Two misunderstandings, frequently arising in Bayesian predictive inference, are discussed. The first deals with the data generating mechanism, while the second consists in overestimating the role played by asymptotic exchangeability. Some c…

• Boundary-Adapted PINNs for Elliptic Dirichlet Problems: $H^2(Ω)$ A Priori Error Bounds with Application to Mean Escape Time Computation
  Nathanael Tepakbong, Jun Fan, Xiang Zhou, Ding-Xuan Zhou · arXiv · Jul 21, 2026

  Motivated by the numerical computation of the Mean Escape Time (MET) $τ:Ω\to\mathbb{R}$ of a stochastic process from a bounded domain $Ω\subseteq\mathbb{R}^d$, we study elliptic Dirichlet boundary value problems (BVPs) using boundary-enforc…

• On the sensitivity of machine-learned probabilistic weather forecast models to scale-aware scoring rules
  Simon Lang, Martin Leutbecher, Sam Hatfield · arXiv · Jul 21, 2026

  Probabilistic forecast models can be machine-learned from data using loss functions based on scoring rules such as the Continuous Ranked Probability Score (CRPS). This note summarises a preliminary study comparing versions of AIFS-CRPS, a g…

• Algebraic Signatures for Structural Learning in Probability Tensors
  Akihiro Maeda, Shohei Hidaka, Satoshi Aoki · arXiv · Jul 21, 2026

  Algebraic statistics characterizes statistical models through polynomial constraints, but it has mainly been used for analytically specified model classes. This paper studies the inverse problem: identifying probabilistic structure from van…

• Elicitation without Backpropagation: Steering Model Behavior by Optimizing the Latent Posterior
  Garrett Baker, Vinayak Pathak, Daniel Murfet, Susan Wei · arXiv · Jul 21, 2026

  In the \emph{latent posterior model} of transformer behavior, the next-token distribution arises from a posterior over latent predictive models conditioned on the context, mixed to generate continuations. We exploit this model in settings w…

• Uncertainty quantification in mechanics: A unified Bayesian perspective
  Sascha Ranftl, Malte Rolf, Gerhard A. Holzapfel, Ellen Kuhl · arXiv · Jul 21, 2026

  Uncertainty quantification (UQ) is essential to experimental mechanics, but has become particularly relevant in computational mechanics, manifesting in two fundamental problem types: forward and inverse problems. The former addresses how in…

• Monetary policy uncertainty and cryptocurrency market uncertainty evidence from time-varying VAR and transmission channels
  Mohamad Husam Helmi, Abdurrahman Nazif Çatık, Coşkun Akdeni̇z, Arya Akdeniz · Eurasian economic review : · Jul 21, 2026

  This paper investigates the impact of monetary policy uncertainty on cryptocurrency market uncertainty using a time-varying parameter vector autoregression (TVP-VAR) model. Unlike previous studies, it jointly employs the shadow rate and the…

• Artificial Intelligence in Space Weather Prediction
  Rajesh K. Mishra, Divyansh Mishra, Rekha Agarwal · International Journal of Ap... · Jul 21, 2026

  Space weather prediction remains a grand challenge due to the nonlinear, multiscale coupling between solar activity, the heliosphere, and Earth’s magnetosphere-ionosphere-thermosphere system. Over the past decade, artificial intelligence (A…

• Structural characteristics and evolutionary mechanisms of the global potash resource trade network: a TERGM-based empirical analysis
  蔡晨蕊, Bo Fu, Shengzhong Huang, Longhui Li · Humanities and Social Scien... · Jul 21, 2026

  With rising agricultural demand, persistent spatial mismatch between potash supply and demand, and increasing uncertainty in global resource supply chains, the structural stability and evolutionary adjustment of the global potash resource t…

• Stochastic Polynomial Surrogate Models for Uncertainty Quantification of Offshore Plate Anchor Capacity
  Negin Yousefpour, B Z Wang, Changjian Zhou, Alessio Mentani · Geotechnical and Geological... · Jul 21, 2026

  Abstract Uncertainty quantification (UQ) is essential for the reliable design of offshore plate anchors, where prediction accuracy is influenced by uncertainties in model parameters, soil properties, loading conditions, and numerical modell…

• PAC--Bayes Bounds on Quotient Parameter Spaces: Geometry-induced Implicit-Bias Priors
  Nicola Aladrah, Fabio Anselmi · arXiv · Jul 20, 2026

  Overparameterized models often have continuous parameter symmetries, so different parameters define the same predictor. We show that PAC--Bayesian analysis should be performed on the quotient predictor space: pushing a prior and posterior t…

• A hybrid deep learning model based on variational auto encoder and probabilistic CS-MSVM for fault detection in PV panels
  Sakina Behilil, Mounia Hendel, Khadra Kessairi, Imen Souhila Bousmaha et al. · Discover Artificial Intelli... · Jul 20, 2026

  Converting energy from solar panels to electric power includes several advantages; it’s considered clean, green, and available. These points make the system a good, attractive, and reliable alternative to electrical power production. Severa…

• Interpretable machine learning for digital soil pH mapping using an optimized AdaBoost algorithm
  Zakiyyan Zain Alkaf, A’isya Nur Aulia Yusuf, Elsa Sari Hayunah Nurdiniyah, Tri Wisudawati · TELKOMNIKA (Telecommunicati... · Jul 19, 2026

  Soil pH is a fundamental parameter determining nutrient availability, microbial activity, and crop productivity. Unlike previous studies that often prioritize prediction accuracy over explainability, this study proposes an interpretable mac…

• A Comprehensive Analysis of Machine Learning Based File Trap Selection Methods to Detect Crypto Ransomware
  Mohan Anand Putrevu, Hrushikesh Chunduri, Venkata Sai Charan Putrevu, Sandeep K Shukla · Digital Threats Research an... · Jul 18, 2026

  The use of multi-threading and file prioritization methods has accelerated the speed at which ransomware encrypts files. To minimize file loss during the ransomware attack, detecting file modifications at the earliest execution stage is con…

• Stochastic and robust modeling of vibration level attenuation in a column drill
  Aslain Brisco Ngnassi Djami, Wolfgang Nzié · Frontiers in Mechanical Eng... · Jul 17, 2026

  Pneumatic column drills are widely used in industrial manufacturing, where vibration significantly affects machining accuracy, equipment durability, and operator safety. This study proposes an uncertainty-aware probabilistic framework for v…

• Probabilistic wave field reconstruction via Bayesian Neural Fields
  Ding Peng Liu, Wen-Huai Tsao, Lance Manuel, Taemin Heo · Applied Ocean Research · Jul 17, 2026

  Reliable characterization of wave energy resources is a prerequisite for the sustainable development of the blue economy, yet it remains challenging due to the spatiotemporal sparsity of satellite altimetry and limited in-situ networks. Thi…

• AutoSurrogate: An LLM-driven multi-agent framework for autonomous construction of deep learning surrogate models in subsurface flow
  Jiale Liu, Nanzhe Wang · Advanced Engineering Inform... · Jul 17, 2026

  High-fidelity numerical simulation of subsurface flow is computationally intensive, especially for many-query tasks such as uncertainty quantification and data assimilation. Deep learning (DL) surrogates can significantly accelerate forward…

• Subjective Risk Decomposition: A New View for Uncertainty Quantification
  Raghad Alamri, Michele Caprio, Gavin Brown · arXiv · Jul 16, 2026

  We present a novel viewpoint for uncertainty quantification. Uncertainty measures are not primitives, in need of axioms and argumentation, but instead consequences, of higher-level modelling decisions. We show how epistemic and aleatoric un…

• cGAP: Generalized Association Plots with HOMALS-Guided Heatmaps for Visualization of High-Dimensional Categorical Data
  Chun-houh Chen, Shun-Chuan Chang, Chiun-How Kao, Yi-Ju Lee et al. · arXiv · Jul 16, 2026

  High-dimensional categorical data arise in genetics, biomedicine, and the social sciences, yet visualization tools for such data remain far less developed than those for continuous variables. Existing methods either scale poorly, rely heavi…