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

• Sparsity Regularized and Robust Mean Variance Portfolio Selection Under Ellipsoidal Uncertainty
  Deniz Akkaya, Emre Can Yayla, Buse Şen, Mustafa Ç. Pınar · arXiv · Sep 10, 2026

  We investigate mean-variance portfolio selection with an $\ell_0$-penalty to promote sparsity in asset allocations. Uncertainty in the mean return vector is incorporated through an ellipsoidal uncertainty set, yielding a robust sparse optim…

• RDDMPI: Residual Denoising Diffusion Model for Probabilistic Multivariate Time Series Imputation
  Ramiro Valdes Jara, David Chapman, Adam Meyers · arXiv · Sep 10, 2026

  Multivariate time series imputation (MTSI) aims to recover missing values in temporal data composed of multiple interdependent variables. This problem is central to real-world applications such as healthcare monitoring, traffic networks, an…

• A distribution-free certification framework for trustworthy crash-severity prediction
  Amir Rafe, Subasish Das · arXiv · Sep 10, 2026

  Crash-severity models inform screening, dispatch and site prioritization, yet are deployed without a finite-sample statement of what one prediction means. Off-the-shelf guarantees fail here, because the features that make crash severity dis…

• Risk-Averse Decision Making with Multi-Level Reliability Guarantees
  Amirmohammad Farzaneh, Osvaldo Simeone · arXiv · Sep 10, 2026

  Many applications in engineering, including wireless broadcasting, require designs that provide performance certificates at different target outage levels. This paper studies the problem of maximizing the weighted average of such certificat…

• Generalized Score Matching for Parameter Estimation on Convex Domains
  Nishanth Shetty, Saisuchith Mahajan, Chandra Sekhar Seelamantula · arXiv · Sep 10, 2026

  Maximum likelihood (ML) estimation is a principled and statistically efficient approach for learning probabilistic models. However, for unnormalized models, ML estimation requires evaluating the partition function and differentiating throug…

• How Wrong Can a Good Predictor Be? Diverging Updates with Vanishing Predictive KL
  Qifu Wen, Shuaijun Liu, Zihan Zhou, Xi Zeng et al. · arXiv · Sep 10, 2026

  Accurate posterior prediction need not require accurate approximation of Bayesian updates. We prove that an unbounded gap between the update maps can coexist with vanishing predictive KL for every fixed finite $K\ge2$ in a stationary symmet…

• Conformal-DRO: Distributionally Robust Optimization with Conformalized Ambiguity Set
  Luhao Zhang, Shixiang Zhu · arXiv · Sep 10, 2026

  Data-driven distributionally robust optimization (DRO) typically treats the conditional outcome law as fixed and uses ambiguity sets to capture estimation error. This paper studies latent distributional heterogeneity, where each instance ha…

• Importance Weighting for Unlabeled-unlabeled Learning under Distribution Shift
  Atsutoshi Kumagai, Tomoharu Iwata, Hiroshi Takahashi, Taishi Nishiyama et al. · arXiv · Sep 10, 2026

  Unlabeled-unlabeled (UU) learning allows us to learn a binary classifier from two sets of unlabeled data with different class-priors. It is a general framework because it includes a wide variety of supervised learning such as positive-unlab…

• Belief updating under strategic deception: Evidence from a classroom voting game
  Tony Syme · International Review of Eco... · Sep 10, 2026

  This paper introduces a classroom game, adapted from the television series The Traitors , that integrates six core concepts from game theory and behavioural economics into a single 25-min activity: asymmetric information, cheap talk, poolin…

• Prequential posteriors
  S. Roy, Richard G. Everitt, Christian P. Robert, Ritabrata Dutta · Japanese Journal of Statist... · Sep 10, 2026

  Abstract Data assimilation is a fundamental task in updating forecasting models upon observing new data, with applications ranging from weather prediction to online reinforcement learning. Deep generative forecasting models (DGFMs) have sho…

• A Unifying Perspective on Probabilities as Model Predictions
  Benedikt Höltgen · arXiv · Sep 9, 2026

  Although probabilistic statements are ubiquitous, foundational disagreements persist about their understanding, as exemplified by debates between Bayesians and frequentists; moreover, it is unclear when and why acting on them actually leads…

• Why Learning Rediscovers the Closed-Form Diagonal Regularizer
  Jeahn Han, Pyojin Kim · arXiv · Sep 9, 2026

  We identify a diagonal saturation principle in modal inverse problems: when truncation noise is isotropic, the Bayes-optimal Tikhonov shape is a closed-form power law Gamma_k proportional to lambda_k^|s| set by the prior alone, independent …

• Bayesian inference of gene regulatory networks at stochastic steady state
  Anshi Gupta, Ryeongkyung Yoon, Krešimir Josić · Journal of The Royal Societ... · Sep 9, 2026

  Gene Regulatory Networks (GRNs) form the regulatory backbone that coordinates gene expression. The architecture of GRNs shapes their function and constraints the biochemical pathways through which information flows. Inferring the structure …

• A Generalization of Amari's Bayesian Duality
  Mohammad Emtiyaz Khan, Thomas Möllenhoff · arXiv · Sep 8, 2026

  Amari's contributions to information geometry and machine learning are well known. Here, we revisit Amari's work on Bayesian duality which has not received as much attention. We connect Amari's Bayesian duality to a convex duality of Bayes'…

• Transformers as In-Context Samplers: From Closed-Form Diffusion to Estimation-Free Sampling
  Arman Adibi, Alireza Jafari, Mohammad Ghavamzadeh, Hadi Daneshmand · arXiv · Sep 8, 2026

  A growing body of work establishes that large language models are not mere statistical memorizers, but are capable of in-context learning: performing inference at test time using only examples provided in the prompt, without any parameter u…

• High-Magnetization Sampling at Low Temperatures: Ising Models and Bayesian Sparse Linear Regression
  Syamantak Kumar, Purnamrita Sarkar, Kevin Tian, Yusong Zhu · arXiv · Sep 8, 2026

  Sparsity is a powerful structural resource in optimization and statistics. We develop frameworks for leveraging sparsity in sampling problems over the Hamming slice $\mathcal{X}_k^d:=\{\mathbf{x}\in\{\pm 1\}^d:|\{i:\mathbf{x}_i=1\}|=k\}$, i…

• The Role of Uncertainty in Assessing the Fairness of Machine Learning Models
  Francesca Panero, Ernst C. Wit, Marco Scutari · arXiv · Sep 7, 2026

  Machine learning models are widely used in clinical applications, social media, law enforcement and critical infrastructure. Verifying whether their outputs are biased against disadvantaged groups or individuals is crucial to ensuring they …

• SGD in Multiclass Logistic Regression: Sequential Learning and Scaling Laws
  Konstantinos Christopher Tsiolis, Denny Wu, Christos Thrampoulidis, Murat A. Erdogdu · arXiv · Sep 7, 2026

  We study the training dynamics of multiclass logistic regression on high-dimensional Gaussian mixture models with a large number of classes and establish precise scaling laws governing the cross-entropy risk under gradient-based optimizatio…

• An AI-driven reconstruction of global surface temperature with emphasis on refining the Antarctic record
  Chenxi Ouyang, Qingxiang Li, Zichen Li, Sihao Wei · Earth system science data · Sep 7, 2026

  Abstract. Accurate estimates of long-term surface temperature (ST) changes are fundamental not only for assessing observed warming, but also for improving the reliability of future climate projections. However, substantial missing informati…

• You KAN do it in a Single Shot: Plug-and-Play Methods with Single-Instance Priors
  Yanqi Cheng, Carola‐Bibiane Schönlieb, Angelica I. Avilés-Rivero · Journal of Mathematical Ima... · Sep 7, 2026
• Prior Information-Assisted Intensity Inhomogeneity Correction Within a Fuzzy Clustering Framework
  International Journal of Bi... · Sep 6, 2026

  The method of utilizing available prior information in the popular FCM algorithm and assesses its benefits in estimating the intensity inhomogeneities and segmenting human brain MRI volumes is studied in this paper. The intensity inhomogene…

• Evaluating parameter-efficient fine-tuning of large language models for sentiment analysis with bayesian optimization
  Raghad Alawaji, Shuaa Alharbi, Haifa Alhasson, Abdulrahman Aloraini · Scientific Reports · Sep 6, 2026

  The increasing volume of user-generated reviews and feedback available in digital format provides valuable insights across various domains. Sentiment analysis plays a crucial role in extracting opinions from textual data. Large Language Mod…

• A novel transformer with soft-cluster prior attention and multi-scale convolution for remaining useful life prediction in air conditioning systems under multi-operating conditions
  Jialiang Chen, Jijia Sun, Guangtao Yao, Sen Xie et al. · Scientific Reports · Sep 5, 2026

  To ensure the stable temperature and humidity environment required for the collection of the university library, accurately predicting remaining useful life for air conditioning system under various operating conditions is of great signific…

• An explainable AI framework for crack width and crack spacing prediction with serviceability-oriented design optimization of reinforced and prestressed concrete members
  Ahmed N. Elbelacy · Journal of Engineering and ... · Sep 5, 2026

  Abstract Reliable prediction of cracking behavior is essential for the serviceability assessment of reinforced and prestressed concrete members, where crack development depends on interacting material, geometric, reinforcement, prestressing…

• Uncertainty-aware Bayesian traffic flow prediction for adaptive signal control
  Zhiyuan Zhou, Lubing Li, Yifan Zhao, Lijuan Wan et al. · Transportation Research Par... · Sep 5, 2026
• Research on decoupling inversion analysis of rockfill dam parameters considering dam zoning and material uncertainty: the case study of a concrete face rockfill dam
  Ran Li, Dangfeng Yang, Chunhui Ma, Yuan Guo et al. · Scientific Reports · Sep 5, 2026

  This paper proposes a parameter decoupling inversion method that integrates sparse polynomial chaos expansion (sPCE) with Bayesian inference. The method aims to accurately investigate the uncertainty in rockfill dam material parameters, imp…

• A Bayesian refinement method incorporating geometric prior and LLM-guided hyperprior for measurement-grade overhang analysis in X-ray electrode inspection
  Tianyu Wang, Shiyu Lu, Tianzhi Li, Chun Cao et al. · Advanced Engineering Inform... · Sep 5, 2026

  Accurate electrode instance identification from X-ray images is essential for reliable overhang analysis in lithium-ion battery electrode inspection. However, industrial X-ray radiographs often exhibit blurred edges, contrast attenuation, a…

• PAC-Bayesian Reconstruction Guarantees for Time Series Variational Autoencoders
  Chloé Hashimoto-Cullen, Ghislain Agoua, Benjamin Guedj, Sylvain Le Corff · arXiv · Sep 4, 2026

  Forecasting time series accurately is critical for applications with complex data ranging from energy systems to healthcare and finance. Among current state of the art models, generative latent variable models are increasingly implemented; …

• Heavy-tail-aware representation learning and dynamic Bayesian state modelling to derive an operational proxy definition of problem gambling risk from routine online gambling data
  Sam Andersson, Helga Westerlind, Timo Koski, Keenan Lyon et al. · EPJ Data Science · Sep 4, 2026

  Abstract Background: Problem gambling causes harm, but operational identification often relies on heuristic thresholds or sparse manual reviews. Routine online gambling logs are heavy-tailed and temporally structured, complicating risk defi…

• Learning the Universe: The Structure of Dust Attenuation Curves in Galaxy Simulations
  Laura Sommovigo, Deaglan J. Bartlett, Rachel K. Cochrane, Matthew Ho et al. · The Astrophysical Journal · Sep 4, 2026

  Abstract Dust attenuation is a major source of systematic uncertainty in both spectral energy distribution (SED) fitting and forward modeling of galaxy populations, yet the functional form used to parameterize attenuation curves has receive…