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

• Data assimilation for subsurface flow using latent diffusion model parameterization: performance of ensemble-Kalman and Monte Carlo techniques
  Guido Di Federico, Wenchao Teng, Louis J. Durlofsky · arXiv · Jun 9, 2026

  Data assimilation (DA) in subsurface flow entails calibrating model parameters to match observed data, typically at wells, while preserving geological realism. Latent diffusion models (LDMs) provide efficient mappings from high-dimensional …

• SPACR: Single-Pass Adaptive Training of Uncertainty-Aware Conformal Regressors
  Soundouss Messoudi, Sylvain Rousseau, Sébastien Destercke · arXiv · Jun 9, 2026

  Conformal Prediction (CP) provides robust uncertainty guarantees for predictive models, but is typically applied post hoc, which misaligns model training with the conformal goal of producing efficient (i.e, narrow) intervals. We propose SPA…

• Decision-Calibrated Conformal Uncertainty for Pacing Decisions in Streaming Advertising
  Prashant Shekhar, Caroline Howard · arXiv · Jun 8, 2026

  We develop a decision-calibrated conformal framework for pacing decisions in streaming advertising. Pacing depends on uncertain future inventory, demand pressure, incremental response, and member-experience load. Instead of calibrating a ge…

• In-Context Learning for Latent Space Bayesian Optimization
  Tuan A. Vu, Harri Lähdesmäki, Julien Martinelli · arXiv · Jun 8, 2026

  Bayesian optimization (BO) is a central tool for sample-efficient design, and latent-space Bayesian optimization (LSBO) extends it to structured objects such as molecules and proteins. In parallel, tabular foundation models such as TabPFN a…

• Report the Floor: A Training-Free Conformal Interval Is a Mandatory Baseline for Probabilistic Time-Series Forecasting
  Valery Manokhin · arXiv · Jun 8, 2026

  Probabilistic forecasters are increasingly learned, yet the baselines they are compared against are often weak or omitted. We show that the simplest possible conformal interval - a last-value point forecast wrapped in a finite-sample split-…

• BSTabDiff: Block-Subunit Diffusion Priors for High-Dimensional Tabular Data Generation
  Al Zadid Sultan Bin Habib, Md Younus Ahamed, Prashnna Gyawali, Gianfranco Doretto et al. · arXiv · Jun 8, 2026

  High-Dimensional Low-Sample Size (HDLSS) tabular domains (e.g., omics) are characterized by $n \ll m$, where $n$ = number of samples, and $m$ = number of features. Such domains often exhibit strong local correlation groups, sparse cross-gro…

• Backward Coherence and Hidden-State Stability in Recurrent Neural Networks: A Quasi-Reverse-Martingale Theory
  Yuan-chin Ivan Chang · arXiv · Jun 8, 2026

  Recurrent neural networks maintain a hidden state $h_t$, but its probabilistic meaning is often unclear. We study hidden-state stability through \emph{backward coherence}: the extent to which $h_t$ can be reconstructed from $h_{t+1}$ by a l…

• Rank Intervals for Leaderboards: A Hierarchical Framework for Model Evaluation
  Bitya Neuhof, Yuval Benjamini · arXiv · Jun 7, 2026

  Pretrained models are often evaluated on multi-task leaderboards to measure their applicability in diverse contexts. However, current methods for aggregating performance across tasks into leaderboard-level rankings do not address the uncert…

• Constructing VAE Latent Spaces with Prescribed Topology
  Jilles S. van Hulst, Jakub M. Tomczak, W. P. M. H. Heemels, Duarte J. Antunes · arXiv · Jun 5, 2026

  Variational autoencoders (VAEs) learn low-dimensional latent representations of high-dimensional data. When the data lies on a manifold with non-Euclidean topology, the standard Gaussian prior introduces a topological mismatch that degrades…

• Causal Atlases from Entropic Inference: Bayesian Networks beyond Optimal DAGs
  Hazhir Aliahmadi, Irina Babayan, Greg van Anders · arXiv · Jun 4, 2026

  Data-driven causal relationship identification is pertinent to advancing understanding of complex systems both within and beyond science. Bayesian networks offer a probabilistic method for modelling generic causal relationships via directed…

• Function-Space Priors for Bayesian Neural ODEs with Application to Vessel Trajectory Prediction
  Jaeyeong Lee, Wonmo Koo, Heeyoung Kim · arXiv · Jun 4, 2026

  Vessel trajectory prediction from Automatic Identification System (AIS) data is essential for maritime situational awareness, yet it remains challenging due to irregular sampling, missing reports, and complex dynamics. Beyond accurate point…

• PAC-Bayesian Adversarially Robust Generalization for Message Passing Graph Neural Networks: A Sensitivity Analysis
  Ziling Liang, Xinping Yi, Qingsong Wen, Shi Jin · arXiv · Jun 4, 2026

  Whilst the vulnerability of graph neural networks (GNNs) to adversarial attacks poses a critical threat to graph representation learning, the understanding of the robust generalization behavior remains a fundamental challenge in the adversa…

• Discrete Causal Representations from Heterogeneous Domains: A Bayesian Approach with Social Survey Applications
  Ankur Garg, Michael Stettler, Aaron Schein, Julius von Kügelgen · arXiv · Jun 4, 2026

  Causal representation learning aims to infer the high-level latent causal concepts that give rise to observed low-level measurements. This is particularly relevant for heterogeneous data from different environments or domains since distribu…

• Dead Directions: Geometric Singular Learning
  Tejas Pradeep Shirodkar · arXiv · Jun 4, 2026

  Singular learning theory and information geometry have studied the same parameter spaces in mostly separate vocabularies: the former computes Bayesian invariants in resolved coordinates, the latter works in original coordinates under a non-…

• Local Preferential Bayesian Optimization
  Johanna Menn, Miriam Kober, Paul Brunzema, David Stenger et al. · arXiv · Jun 1, 2026

  Bayesian optimization (BO) is a popular and effective approach for tuning expensive, noisy experiments, but requires the formulation of an explicit objective function. Preferential BO (PBO) removes this requirement by learning from pairwise…

• ShaplEIG: Bayesian Experimental Design for Shapley Value Estimation
  David Rundel, Fabian Fumagalli, Maximilian Muschalik, Bernd Bischl et al. · arXiv · Jun 1, 2026

  Shapley values are a principled attribution measure widely used in interpretable machine learning, but their exact computation scales exponentially with the number of players, motivating a wide range of approximation methods based on value …

• Bayesian meta-learning for modeling Alzheimer's disease progression
  Clara Hoffmann, Nadja Klein · arXiv · Jun 1, 2026

  Predicting whether an individual with Alzheimer's disease will experience mild or severe disease progression is essential for personalized treatment. Typically, practitioners seek to predict the distribution of a discrete disease score, con…

• ProbRes: Volatility Learning for Probabilistic Time-Series Forecasting
  Tingting Wang, Yunyi Zhang, Benyou Wang · arXiv · Jun 1, 2026

  Probabilistic time series forecasting has attracted increasing attention in financial applications due to the need to quantify risk and uncertainty in future observations. We propose ProbRes, a post-hoc probabilistic calibration method that…

• Decision-calibrated prediction sets for robust power system operations
  Akylas Stratigakos, Honglin Wen, Elina Spyrou, Pierre Pinson · arXiv · Jun 1, 2026

  Robust optimization offers a tractable approach to balance operating costs and reliability in power systems dominated by weather-dependent renewable uncertainty, but its performance depends critically on the uncertainty set. Standard data-d…

• PliableBVS: A flexible Bayesian variable selection method for modeling interactions with mandatory modifying variables
  Theophilus Quachie Asenso, Zhi Zhao, Maren-Helene Langeland Degnes, Marie Cecilie Paasche Roland et al. · arXiv · Jun 1, 2026

  High-dimensional interaction models are useful for studying, for example, how a large set of variables of interest, such as gene expression or other omics features, interact with a smaller set of modifying variables, such as clinical covari…

• Flow-Transformed Implicit Processes for Function-Space Variational Inference
  Luis A. Ortega, Andrés R. Masegosa, Thomas D. Nielsen · arXiv · Jun 1, 2026

  Implicit-process priors define distributions over functions through flexible generative mechanisms, making them attractive for Bayesian function-space modelling. However, performing posterior inference with such priors is challenging becaus…

• Data-Automated Policy Learning for Nonlinear Welfare
  Chunrong Ai, Zeqi Wu, Zheng Zhang · arXiv · Jun 1, 2026

  This paper explores policy learning from observational data, focusing on a nonlinear welfare criterion in a binary treatment setting. The nonlinear criterion is inspired by scenarios where policymakers prioritize specific population segment…

• MINTS: Minimalist Thompson Sampling
  Kaizheng Wang · arXiv · Jun 1, 2026

  The Bayesian paradigm offers principled tools for sequential decision-making under uncertainty, but its reliance on a probabilistic model for all parameters can hinder the incorporation of complex structural constraints. We introduce a mini…

• The Dynamic-Probabilistic Consistency Gap in Chaotic Surrogate Modeling
  Andre Herz, Matthijs Pals, Daniel Durstewitz, Georgia Koppe · arXiv · May 29, 2026

  Dynamical systems reconstruction (DSR) aims to learn surrogate models that capture the dynamics underlying time-series data. Reliably deploying these surrogates requires uncertainty estimates consistent with the learned dynamics. We expose …

• Memory by Design: Probabilistic Sequence Layers
  Matthew Dowling, Hyungju Jeon, Cristina Savin, Il Memming Park · arXiv · May 29, 2026

  We introduce the design-model framework: a way to derive efficient recurrent sequence maps from explicit assumptions about memory. A design model writes evidence into memory by exact Bayesian filtering; a query-dependent readout produces a …

• Model-Agnostic Signal Discovery with Machine Learning: Bridging the Gap Between Theory and Practice
  Oz Amram, Marco Letizia, Mikael Kuusela · arXiv · May 29, 2026

  Searches for new phenomena in complex scientific data are predominantly model-dependent, optimized for specific hypotheses, and therefore limited in their coverage of the space of possible signals. Recently, new AI-based model-agnostic sear…

• Forecasting threshold exceedance of atmospheric variables at a specific location
  Roberta Baggio, Jean-François Muzy · arXiv · May 29, 2026

  This study compares two methodological approaches for predicting, at a given site, threshold exceedances of atmospheric variables such as temperature and wind speed: (i) direct probabilistic methods, which treat exceedance as a binary class…

• On Language Generation in the Limit with Bounded Memory
  Jon Kleinberg, Anay Mehrotra, Amin Saberi, Grigoris Velegkas · arXiv · May 28, 2026

  We study language generation in the limit under bounded memory. In this task, a learner observes examples from an unknown target language one at a time and must eventually output only new valid examples. Prior work assumes access to the ent…

• Conformal Certification of Reasoning Trace Prefixes
  Matt Y. Cheung, Ashok Veeraraghavan, Hanjie Chen, Guha Balakrishnan · arXiv · May 28, 2026

  Language model reasoning traces are rarely all-or-nothing; they frequently contain valid intermediate steps before a critical error occurs. Existing uncertainty quantification methods typically certify final answers or entire responses, fai…

• Joint Model and Data Sparsification via the Marginal Likelihood
  Alexander Timans, Thomas Möllenhoff, Christian A. Naesseth, Mohammad Emtiyaz Khan et al. · arXiv · May 28, 2026

  Sparse recovery in linear systems underpins applications from signal processing to high-dimensional regression. Sparse Bayesian Learning, grounded in the principle of automatic relevance determination (ARD), offers a practical Bayesian mech…