Develops methods for constructing likelihoods and priors for Bayesian networks.
problem Learning parameters and structure of Bayesian networks from limited data.
method Introduces assumptions for constructing likelihoods and priors from small assessments.
result Allows construction of likelihoods and priors for a wide range of network structures.
New priors for deep neural networks converge to Gaussian processes.
problem Improving the performance and stability of deep neural networks.
method Extending prior distributions to include non-zero means and partially exchangeable priors, leading to a new Gaussian process model.
result The new Gaussian process model avoids pathologies and improves performance on regression problems.
Improved MRI head anatomy segmentation using deep learning with multiple priors.
problem Challenges in segmenting head anatomy in MRI, especially with lesions.
method Added three types of prior information to a 3D convolutional network: spatial priors, morphological priors, and spatial context.
result Multiprior network improves segmentation performance, especially for abnormal anatomies.
New method recovers signals from compressed measurements using generative networks with contractive layers.
problem Signal recovery from compressed measurements with generative network priors.
method Developed a new matrix concentration inequality (R2WDC) to relax expansivity conditions for generative networks.
result Signals in the range of a Gaussian generative network can be recovered from few linear measurements with contractive layers.
New method learns fusion rules from few images using granular ball priors.
problem Challenges in supervised learning for image fusion with limited data.
method Introduces incomplete priors and Granular Ball Pixel Computation (GBPC) algorithm.
result Lightweight neural network learns effective fusion rules from few images.
PriorGrad improves speech synthesis models by using data-dependent adaptive priors.
problem Inefficiency in denoising diffusion models due to mismatch between prior and data distributions.
method Proposes PriorGrad, an adaptive prior derived from data statistics based on conditional information.
result PriorGrad achieves faster convergence and superior performance in speech synthesis models.
In this paper we develop a novel neural network model for predicting implied volatility surface. Prior financial domain knowledge is taken into account. A new activation function that incorporates volatility smile is proposed, which is used for the hidden nodes that process the underlying asset price. In addition, fina…
CSNE embeds signed networks by separating structural and fine-grained information.
problem Improving sign prediction in signed networks using inaccurate or incomplete balance theories.
method Conditional Signed Network Embedding (CSNE) models structural and fine-grained information separately, integrating them rigorously.
result CSNE outperforms state-of-the-art on sign prediction tasks, and MaxEnt priors are competitive in resource-constrained settings.
PD-PINNs accelerate PINN training by incorporating task-specific dictionaries.
problem Training PINNs is slow and lacks theoretical error bounds.
method Integrates task-dependent dictionaries into PINNs to enhance convergence.
result PD-PINNs achieve faster convergence and bounded prediction errors.
A new prior improves generative models' performance.
problem Mode collapse and poor evidence lower bound in GANs and VAEs.
method Tensor Ring Induced Prior (TRIP) that packs many Gaussians into a lattice.
result TRIP improves FID for GANs and ELBO for VAEs.
We establish large deviation principles for convolutional neural networks.
problem Understanding the behavior of convolutional neural networks in the infinite-channel limit.
method We establish large deviation principles for convolutional neural networks under Gaussian prior and posterior distributions.
result We provide a large deviation principle for the sequence of conditional covariance matrices and the posterior distribution.
A new meta-learning method using shared variational inference.
problem Meta-learning with uncertainty over model parameters.
method Shared amortized variational inference network for conditional prior and posterior.
result Prevents collapse of conditional prior to Dirac delta function.
Bayesian PINNs learn elliptic PDEs with near-minimax posterior contraction rate.
problem Learning elliptic PDEs with noisy data and non-homogeneous boundary conditions.
method Bayesian approach with a Hölder space prior on neural network weights.
result Posterior contracts at near-minimax rate without prior knowledge of solution smoothness.
Polynomial-time algorithm learns ReLU networks without assumptions.
problem Learning linear combinations of ReLU activations with Gaussian inputs.
method Random contractions of moment tensors and multi-scale analysis.
result First polynomial-time algorithm without additional assumptions.
Extends VAEs to handle complex Bayesian network structures.
problem Handling complex dependency structures in Bayesian networks.
method Extends VAEs with graphical residual flows to model arbitrary dependency structures.
result Demonstrates improved performance on synthetic datasets.
Bayesian neural networks with dependent weights converge to Gaussian mixtures.
problem Limitations of standard Gaussian priors in neural networks.
method Posterior analysis with Gaussian likelihood for networks with dependent weights.
result Posterior distribution identified in the wide-width limit, ensuring invertibility of random covariance matrix.
Gradient descent with logistic loss can interpolate deep networks with smoothed ReLU activations under certain conditions.
problem Conditions for gradient descent to drive logistic loss to zero in deep networks with smoothed ReLU activations.
method Gradient descent applied to fixed-width deep networks with smoothed ReLU approximations (e.g., Swish, Huberized ReLU).
result Gradient descent can drive logistic loss to zero under specific conditions, providing bounds on convergence rate.
New method uses trainable activations to make BNNs behave like GPs.
problem Making Bayesian Neural Networks (BNNs) behave like Gaussian Processes (GPs).
method Introduced trainable activations and periodic activations to map GP priors to BNNs. Used 2-Wasserstein distance for optimization.
result Method consistently outperforms existing approaches or matches heuristic methods.
New analysis shows reconstruction attacks are unreliable without prior data knowledge.
problem Privacy and security risks from neural network memorization of training data.
method Complementary analysis of reconstruction methods, proving their unreliability without prior data knowledge.
result Reconstruction attacks are fundamentally unreliable without prior data knowledge, and networks trained more extensively are less susceptible.
Researchers derive exact priors for finite Bayesian neural networks.
problem Understanding non-Gaussian priors in finite Bayesian neural networks.
method Analytical derivation of function space priors for finite fully-connected feedforward networks.
result Exact solutions for priors of finite networks, including Meijer G-function for linear networks and mixtures for ReLU networks.
Paper presents ML-VAMP for efficient multi-layer inference with exact performance analysis.
problem Inference in multi-layer deep neural networks with non-convex optimization.
method ML-VAMP algorithm for MAP and MMSE estimates, with performance predictions in high dimensions.
result ML-VAMP achieves Bayes-optimal MSE under certain conditions, providing exact performance characterization.
A neural network derived from first principles using MaxEnt.
problem Developing a neural network from first principles.
method Derived a neural network using the principle of Maximum Entropy, with linear dimension-reducing transformations and conditional mean estimators.
result Unified theoretical justification for activation functions like sigmoid, softplus, and relu.
In the Bayesian approach to structure learning of graphical models, the equivalent sample size (ESS) in the Dirichlet prior over the model parameters was recently shown to have an important effect on the maximum-a-posteriori estimate of the Bayesian network structure. In our first contribution, we theoretically analyze…
Deep neural networks excel at function approximation, yet they are typically trained from scratch for each new function. On the other hand, Bayesian methods, such as Gaussian Processes (GPs), exploit prior knowledge to quickly infer the shape of a new function at test time. Yet GPs are computationally expensive, and it…
Bayesian imaging uses neural networks to learn prior knowledge from data.
problem Performing Bayesian inference in imaging problems with limited prior knowledge.
method Constructs a data-driven prior on a sub-manifold of the image space using neural networks, and performs Bayesian computation on this manifold.
result Established the existence and well-posedness of the posterior distribution and moments, and demonstrated superior performance compared to existing methods.
Bayesian priors for neural networks are improved by incorporating weight correlations and tail behavior.
problem Improving Bayesian priors for neural networks to better reflect true beliefs and performance.
method Analyzed summary statistics of neural network weights in different architectures and incorporated these observations into new priors.
result Improved performance on image classification datasets by using new priors that account for weight correlations and tail behavior.
Bayesian approach for solving systems of linear PDEs with boundary conditions.
problem Modeling data efficiently with prior knowledge from systems of linear PDEs.
method Construct multi-output Gaussian process priors using Gröbner bases and pullback parametrizations.
result Gaussian process priors can represent solutions to systems of linear PDEs adhering to boundary conditions.
Bayesian neural networks use ridgelet prior for uncertainty quantification.
problem Combining strong predictive performance with uncertainty quantification in Bayesian neural networks.
method Proposes a ridgelet prior that approximates a Gaussian process covariance function in the output space of the network.
result Establishes universality property allowing Bayesian neural networks to approximate any Gaussian process.
Bayesian method uses deep learning prior for CT reconstruction.
problem Imaging inverse problems in CT reconstruction.
method SA-Roundtrip prior with HMC-pCN sampler.
result Outperforms state-of-the-art methods in CT reconstruction.
TSFlow uses Gaussian processes to match priors for better time series forecasting.
problem Difficulties in aligning generative models' priors with time series data.
method Conditional flow matching (CFM) with Gaussian processes, optimal transport, and data-dependent priors.
result TSFlow produces high-quality unconditional samples and competitive forecasting results.
Regression Prior Networks improve ensemble performance on regression tasks.
problem Improving ensemble performance on regression tasks.
method Extending Prior Networks and Ensemble Distribution Distillation (EnD2) to regression tasks using the Normal-Wishart distribution. result Regression Prior Networks yield performance competitive with ensemble approaches on regression tasks.
BNNpriors library improves Bayesian neural network inference with various prior distributions.
problem Challenges in choosing good prior distributions for Bayesian neural networks.
method State-of-the-art Markov Chain Monte Carlo inference with a wide range of predefined priors.
result Facilitates foundational discoveries on the nature of the cold posterior effect.
Proposes a new model for predicting chronic conditions over time.
problem Predicting complex relationships between multiple chronic conditions.
method Continuous time Bayesian network with adaptive regularization for structure and parameter learning.
result Proposed model provides sparse, intuitive representation of chronic condition relationships.
Variational dropout (VD) is a generalization of Gaussian dropout, which aims at inferring the posterior of network weights based on a log-uniform prior on them to learn these weights as well as dropout rate simultaneously. The log-uniform prior not only interprets the regularization capacity of Gaussian dropout in netw…
We propose a novel method for network inference from partially observed edges using a node-specific degree prior. The degree prior is derived from observed edges in the network to be inferred, and its hyper-parameters are determined by cross validation. Then we formulate network inference as a matrix completion problem…
Bayesian method learns network structure from Gaussian process priors.
problem Computational infeasibility of Bayesian structure learning in GPNs.
method Monte Carlo and MCMC methods for sampling network structures.
result Method outperforms state-of-the-art algorithms in recovering network structure.
This work tackles the challenge of Bayesian deep learning by proposing a new framework for matching Gaussian process priors with neural network parameters.
problem The challenge of specifying priors over neural network parameters, which affects the induced functional prior and is uncontrolled.
method The approach involves defining functional priors using Gaussian processes and matching these priors with the functional prior of neural networks through the minimization of Wasserstein distance.
result The proposed framework offers systematic performance improvements over alternative priors and approximate Bayesian deep learning approaches.
This paper improves Prior Networks for uncertainty and adversarial robustness.
problem Improving uncertainty and adversarial robustness in classification models.
method Introduces reverse KL-divergence for training Prior Networks and proposes a generalized adversarial training method.
result Prior Networks trained with reverse KL-divergence show improved out-of-distribution detection and are harder to evade in adversarial attacks.
Proposes DSM priors for Bayesian neural networks to improve interpretability and robustness.
problem Bayesian neural networks struggle with interpretability, overconfidence, and adversarial attacks.
method Introduces Dirichlet scale mixture (DSM) priors to address these issues.
result DSM priors lead to sparse networks, robustness against adversarial attacks, and competitive predictive performance.
Enhances neural networks with prior function values to improve accuracy.
problem Improving neural network accuracy in regions without training data.
method Develops a probabilistic approach to augment BNNs with prior function values.
result Predictions rely more on prior information in uncertain regions.
Bayesian neural networks are shown to be minimax and admissible under certain conditions.
problem Optimality of Bayesian neural networks in deep learning models.
method Analysis of decision rules induced by BNNs in the normal location model under quadratic loss.
result A hyperprior on the effective output variance yields a minimax and admissible decision rule.
Bayesian weight priors improve neural network learning of identity relations.
problem Neural networks struggle to learn abstract and systematic relations, especially identity relations.
method Extended RBP approach using Bayesian weight priors as a regularization term.
result Bayesian weight priors lead to perfect generalization for identity relations and do not hinder standard neural network learning.
Learning the network structure underlying data is an important problem in machine learning. This paper introduces a novel prior to study the inference of scale-free networks, which are widely used to model social and biological networks. The prior not only favors a desirable global node degree distribution, but also ta…
New algorithm uses untrained neural networks for image recovery, offering better compression.
problem Using untrained neural networks for image recovery and theoretical guarantees.
method Projected gradient descent scheme for solving linear and non-linear inverse problems.
result The method achieves better compression rates for the same image quality compared to hand-crafted priors.
Bayesian neural network achieves nearly optimal performance in Besov space.
problem Bayesian neural networks in Besov space.
method Spike-and-slab prior and shrinkage prior for posterior convergence rate.
result The posterior convergence rate is nearly minimax and adaptive to unknown smoothness.
Paper improves speech separation by using deep neural networks for more accurate density priors.
problem Improving the accuracy of source priors for independent vector analysis in speech separation.
method Estimating the derivative of speech density using deep neural networks to optimize performance indices.
result Neural network density priors outperform previous ones in convergence speed and SIR.
This work explores how overparametrization and priors affect Bayesian neural network posteriors.
problem Symmetries, non-identifiabilities, and weight-space priors fragment and inflate BNN posteriors.
method We study the interplay between overparametrization and priors in BNN posteriors, deriving key phenomena and validating through experiments.
result Overparametrization induces structured, prior-aligned weight posterior distributions.
Unified framework for Bayesian PDE-constrained inversion using physics-informed neural networks.
problem Incorporating prior distributions in function space into Bayesian PINN-based inversion.
method Functional-prior-based approaches (fpBPINN) to Bayesian PDE-constrained inversion using physics-informed neural networks (PINNs). Two complementary approaches: FPI-BPINN and fParVI-PINN.
result Accurate estimation of posterior distributions in seismic traveltime tomography and Darcy-flow permeability inversion.