arXiv research

Transformers can simulate MLE for Bayesian network sequences.

This paper offers a simple method for Bayesian regression with unknown transformations.

Bayesian model for discrete data with conditional transformations.

Study on Bayesian transformers finds issues with weight-space inference and prior specification.

A new method improves likelihood-free Bayesian inference by transforming summary statistics and using efficient Variational Bayes.

Transformers mimic Bayesian reasoning in controlled settings, revealing geometric mechanisms.

Bayesian quadrature improves integration efficiency with invariant priors.

Hybrid approach combines transformer and Bayesian filtering for robust multiple particle tracking.

TM-VI uses flexible transformation models to approximate complex posteriors in Bayesian models.

A new Bayesian image segmentation algorithm is proposed by combining a loopy belief propagation with an inverse real space renormalization group transformation to reduce the computational time. In results of our experiment, we observe that the proposed method can reduce the computational time to less than one-tenth of …

A new Bayesian modeling method is proposed by combining the maximization of the marginal likelihood with a momentum-space renormalization group transformation for Gaussian graphical models. Moreover, we present a scheme for computint the statistical averages of hyperparameters and mean square errors in our proposed met…

To model categorical response variables given their covariates, we propose a permuted and augmented stick-breaking (paSB) construction that one-to-one maps the observed categories to randomly permuted latent sticks. This new construction transforms multinomial regression into regression analysis of stick-specific binar…

Bayesian analysis reveals epistemic uncertainty as a key diagnostic for delayed generalization in in-context learning.

New proof of injectivity for broken non-abelian X-ray transform in Minkowski space.

Characterizes Bayesian networks up to unconditional equivalence.

Normalizing flows are shown to be equivalent to Bayesian networks, revealing new insights.

Transformer pretraining yields strong EB performance without explicit adaptation.

New method improves reliability of depth estimation models.

Transformers prefer simpler explanations in hierarchical tasks.

Variational inference provides approximations to the computationally intractable posterior distribution in Bayesian networks. A prominent medical application of noisy-or Bayesian network is to infer potential diseases given observed symptoms. Previous studies focus on approximating a handful of complicated pathological…

SGPA calibrates transformer uncertainty for safety-critical tasks.

Traditional GANs use a deterministic generator function (typically a neural network) to transform a random noise input $z$ to a sample $\mathbf{x}$ that the discriminator seeks to distinguish. We propose a new GAN called Bayesian Conditional Generative Adversarial Networks (BC-GANs) that use a random generator function…

Bayesian Scattering offers a simple baseline for image data uncertainty.

Fast Bayesian inference with adaptable priors for real-time applications.

We present an improved Bayesian framework for performing inference of affine transformations of constrained functions. We focus on quadrature with nonnegative functions, a common task in Bayesian inference. We consider constraints on the range of the function of interest, such as nonnegativity or boundedness. Although …

Simformer uses transformer models to perform flexible Bayesian inference.

BayesDLL offers a PyTorch library for Bayesian deep learning with large models.

Transformers approximate Bayesian posteriors but not exactly.

A major challenge in Bayesian Optimization is the boundary issue (Swersky, 2017) where an algorithm spends too many evaluations near the boundary of its search space. In this paper, we propose BOCK, Bayesian Optimization with Cylindrical Kernels, whose basic idea is to transform the ball geometry of the search space us…

Bayesian approach optimizes in-context learning for state space models.

Paper derives a simplified formula for Expected Improvement using log-transformed data.

Novel regularization for Vision Transformers improves model generalization and sparsity.

ICEE learns new RL tasks in less time with a Transformer model.

Transformers can approximate Bayesian inference efficiently.

Bayesian design improves experimental optimization.

Bayesian Transformer improves probabilistic load forecasting with calibrated uncertainty estimates.

This paper compares amortized methods for Bayesian posterior estimation.

Graphical normalizing flows use Bayesian networks to improve normalizing flows' interpretability and performance.

Transformers can approximate posterior predictive distributions through in-context learning.

We revisit Rahimi and Recht (2007)'s kernel random Fourier features (RFF) method through the lens of the PAC-Bayesian theory. While the primary goal of RFF is to approximate a kernel, we look at the Fourier transform as a prior distribution over trigonometric hypotheses. It naturally suggests learning a posterior on th…

Improved phylogenetic inference with normalizing flows.

Joint alignment of a collection of functions is the process of independently transforming the functions so that they appear more similar to each other. Typically, such unsupervised alignment algorithms fail when presented with complex data sets arising from multiple modalities or make restrictive assumptions about the …

Novel framework analyzes economic shifts in data-poor economies.

Computation of moments of transformed random variables is a problem appearing in many engineering applications. The current methods for moment transformation are mostly based on the classical quadrature rules which cannot account for the approximation errors. Our aim is to design a method for moment transformation for …

New analysis shows how cross-entropy training shapes attention in transformers.

This study examines how large language models learn in-context and provides insights into their performance and architecture.

Bayesian method improves reliability of BERT for hate speech detection.

New method for uncertainty analysis in TabPFN, a state-of-the-art tabular transformer.