Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,341 papers · 148 categories

Trend · papers per month

2765528271,103 · Jun 202019922001200920182026
48 results for generalized Bayesian

FP-BMA improves generalization by encouraging flat posteriors in Bayesian Model Averaging.

problem Lack of flat posterior in approximate Bayesian inference methods hinders effective Bayesian Model Averaging.
method Proposes Flat Posterior-aware Bayesian Model Averaging (FP-BMA) and Flat Posterior-aware Bayesian Transfer Learning schemes.
result FP-BMA successfully captures flat posteriors, improving generalization performance.

Link between PAC-Bayesian bounds and Bayesian marginal likelihood.

problem Understanding the connection between frequentist and Bayesian approaches in risk minimization.
method Exhibit a strong link between PAC-Bayesian risk bounds and Bayesian marginal likelihood, especially for the negative log-likelihood loss function.
result PAC-Bayesian minimization maximizes Bayesian marginal likelihood, providing an alternative to Bayesian Occam's razor.

Bayesian methods enhance deep learning models by improving reliability and uncertainty.

problem Improving reliability and uncertainty awareness in deep learning models.
method Approximate Bayesian inference techniques, including SG-MCMC and VI, applied to deep learning models.
result Enhanced posterior inference for deep learning models, particularly in neural networks and generative models.

Bayesian neural networks use temperature adjustments to improve predictive performance.

problem Lack of theoretical generalization guarantees for Bayesian neural networks.
method Temperature adjustments to balance likelihood and prior regularization.
result Improved predictive performance through temperature adjustments.

Paper analyzes the free energy of CNNs with skip connections in Bayesian learning.

problem Dependency of CNNs with skip connections on the number of parameters.
method Examines the Bayesian free energy of CNNs with and without skip connections.
result The upper bound of free energy of Bayesian CNN with skip connections does not depend on overparametrization.

Bayesian regularizations are explicitly implemented in CNNs, improving deep learning generalization.

problem Improving generalization in deep learning models.
method Introduced a novel probabilistic representation for CNN hidden layers and demonstrated their Bayesian nature.
result CNNs have explicitly Bayesian regularizations based on Bayesian regularization theory.

This research improves PAC-Bayesian bounds for classification tasks using convexified loss.

problem Deriving generalization bounds for classification tasks with non-convex loss functions.
method Shift focus to misclassification excess risk bounds for PAC-Bayesian classification using convex surrogate loss and leveraging PAC-Bayesian relative bounds in expectation.
result Improved PAC-Bayesian bounds for classification tasks with convex surrogate loss.

Bayesian optimization improves chemical design by avoiding invalid molecules.

problem Bayesian optimization over variational autoencoder latent space produces invalid molecular structures.
method Formulated constrained Bayesian optimization to avoid querying far from training data.
result Marked improvements in validity of generated molecules.

Inference in popular nonparametric Bayesian models typically relies on sampling or other approximations. This paper presents a general methodology for constructing novel tractable nonparametric Bayesian methods by applying the kernel trick to inference in a parametric Bayesian model. For example, Gaussian process regre…

2011-03-09abs ↗pdf ↗

FBMS R package simplifies Bayesian model selection and averaging.

problem Complex regression settings with multi-modal posterior landscapes.
method Efficient MJMCMC and GMJMCMC algorithms for Bayesian model exploration.
result FBMS effectively handles Bayesian generalized linear and nonlinear models.

Bayesian deep learning improves neural network accuracy and generalization.

problem Improving accuracy and calibration of deep neural networks.
method Bayesian marginalization and deep ensembles to approximate marginalization, and tempering for calibrating predictive distributions.
result Bayesian approaches improve deep neural networks' accuracy and generalization.

SOLBP extends efficient inference to uncertain Bayesian networks.

problem Inference in uncertain Bayesian networks with second-order probabilities.
method Extends Loopy Belief Propagation to second-order Bayesian networks.
result Generates inferences consistent with sum-product networks, more efficient and scalable.

Paper revisits weighted likelihood bootstrap and extends it to loss-likelihood bootstrap.

problem Generating samples from approximate Bayesian posterior of a parametric model.
method Bayesian nonparametric model with minimising expected negative log-likelihood.
result Loss-likelihood bootstrap method for posterior sampling.

Paper develops robust Bayesian models for linear regression under adversarial perturbations.

problem Ensuring reliable machine learning models under data perturbations.
method Formulates adversarial Bregman divergence loss, computes adversarial perturbation, introduces adversarially robust posteriors, derives generalization certificates.
result Derives first rigorous generalization certificates for adversarially robust Bayesian linear regression.

New analysis shows Bayesian model averaging is suboptimal under misspecification.

problem Generalization performance of Bayesian model averaging under model misspecification.
method Novel second-order PAC-Bayes bounds to analyze generalization performance.
result New Bayesian-like algorithms with better generalization performance.

Transformers can simulate MLE for Bayesian network sequences.

problem Understanding transformers' capabilities in Bayesian network sequence generation.
method In-context maximum likelihood estimation (MLE) for autoregressive sequence generation.
result A simple transformer model can estimate Bayesian network probabilities and generate new samples.

Bayesian CycleGAN improves cycle-consistent GANs by stabilizing training and diversifying generated images.

problem Challenges in stabilizing training of cycle-consistent GANs leading to mode collapse.
method Proposes a Bayesian approach to stabilize training and diversify generated images.
result Improves per-pixel accuracy by 15% on Cityscapes semantic segmentation task and 20% on Monet2Photo style transfer.

Bayesian framework for encoding uncertainty and inducing sparsity.

problem Handling uncertainty and inducing sparsity in statistical models.
method General Bayesian framework with explicit encoding of uncertainty and sparsity-inducing approach.
result Effective in linear and logistic regression, and Bayesian neural networks.

The paper introduces new Bayesian network classifiers for better classification accuracy.

problem Improving supervised classification accuracy using Bayesian network classifiers.
method Developed novel classes of generative classifiers based on staged tree models, extending Bayesian networks.
result Data-driven learning routines enhance the accuracy of the new classifiers.

Bayesian Deep Learning tackles inverse problems with neural networks and approximate computations.

problem Solving inverse problems with indirect measurements and uncertainties.
method Bayesian Deep Learning, using neural networks and approximate computations.
result Effective solutions for inverse problems using Bayesian Deep Learning.

This paper relaxes PAC-Bayesian assumptions for dependent, heavy-tailed data.

problem Connecting the generalization ability of an aggregation distribution to empirical risk and KL divergence.
method Introduces PAC-Bayesian bounds using Csiszár's ff-divergence for dependent, heavy-tailed data.
result Provides simplified PAC-Bayesian bounds for hostile data.

The study examines how equivariance in networks affects generalization error using PAC-Bayesian bounds.

problem Understanding how equivariance in networks impacts generalization error.
method Utilized PAC-Bayesian analysis for equivariant networks, deriving norm-based bounds for generalization error.
result The bound indicates that using larger group size in the model improves generalization error.

The study improves PAC-Bayesian bounds for adversarial generative models.

problem Improving generalization bounds for adversarial generative models.
method Extending PAC-Bayesian theory to generative models, developing bounds for Wasserstein and total variation distances.
result New training objectives for Wasserstein and Energy-Based GANs.

PAC-Bayesian theory applied to data-dependent hypothesis sets yields uniform generalization bounds.

problem Proving uniform generalization bounds for data-dependent hypothesis sets.
method Applying PAC-Bayesian framework on 'random sets' and considering data-dependent hypothesis sets.
result Data-dependent uniform generalization bounds are proven, providing tighter and unified results.

Enhanced Bayesian target encoding uses sampling techniques to improve model performance.

problem Improving target encoding for better model performance in machine learning.
method Using sampling techniques in Bayesian target encoding to extract intra-category distribution information.
result Improves generalization and reduces target leakage in machine learning models.

Proposes a Bayesian Autoencoder with sparse Gaussian process priors to capture data correlations.

problem Autoencoders' i.i.d. assumption of latent representations fails to capture data correlations.
method Imposes fully Bayesian sparse Gaussian Process priors on the latent space of a Bayesian Autoencoder and uses stochastic gradient Hamiltonian Monte Carlo for posterior estimation.
result Consistently outperforms alternatives relying on Variational Autoencoders on various tasks.

Generative approach speeds hyperparameter tuning for machine learning models.

problem Computational infeasibility of cross-validation and difficulty of fully Bayesian hyper-parameter learning.
method Combines optimization-based approximations and amortization techniques.
result Rapid evaluation of hyper-parameters over grids or ranges, supporting predictive tuning and uncertainty quantification.

FHBI enhances generalization in Bayesian inference with iterative steps in functional spaces.

problem Improving generalization in Bayesian inference models.
method Iterative two-step procedure with adversarial and functional descent steps in a reproducing kernel Hilbert space.
result FHBI consistently outperforms nine baseline methods on the VTAB-1K benchmark.

The paper proposes using path signatures for better inference in time series data.

problem Simulation models with time series data often lack tractable likelihood functions.
method Approximate Bayesian Computation with path signatures to handle sequential data.
result Theoretical guarantees on the resultant posteriors for Bayesian parameter inference.

Bayesian approach improves semi-supervised learning with deep generative models.

problem Lack of model uncertainty and flexibility in existing semi-supervised learning methods.
method Proposes a discriminative component with stochastic inputs and extends it to be fully Bayesian.
result Improved handling of model uncertainty and flexibility in capturing complex patterns.

Bayesian free energy remains bounded for deep ReLU networks in overparametrized cases.

problem Understanding the generalization performance of deep ReLU neural networks.
method Analyzes Bayesian free energy in overparametrized deep ReLU neural networks.
result Bayesian free energy is bounded even in overparametrized deep ReLU networks.