Proposes learning a hierarchical prior in VAEs to avoid over-regularization.
problem Over-regularization in VAEs with standard normal priors.
method Formulates as a constrained optimisation problem, introduces graph-based interpolation.
result Learned latent representation reflects data manifold topology and properties.
Bayesian Hierarchical Invariant Prediction refines ICP for better scalability and prior integration.
problem Improving computational scalability and invariance testing for causal inference.
method Bayesian Hierarchical structure to test invariance under heterogeneous data.
result Demonstrated improved scalability and potential as an alternative to ICP.
Common statistical practice has shown that the full power of Bayesian methods is not realized until hierarchical priors are used, as these allow for greater "robustness" and the ability to "share statistical strength." Yet it is an ongoing challenge to provide a learning-theoretically sound formalism of such notions th…
VBD improves variational dropout by using a hierarchical prior, enabling better regularization.
problem Improper log-uniform prior in VD causes ill-posed posterior inference.
method Introduces a hierarchical prior with a zero-mean Gaussian distribution and a uniform hyper-prior.
result VBD enables well-posed posterior inference and superior regularization performance.
A hierarchical Gaussian prior model improves low-rank matrix completion.
problem Low-rank matrix completion with improved structure exploitation.
method Hierarchical Gaussian prior model with GAMP embedded variational Bayesian inference.
result The proposed method outperforms state-of-the-art matrix completion methods.
Proposes a method to improve hierarchical clustering using set-level structural priors.
problem Lack of supervision for non-leaf structure in hierarchical clustering.
method Introduces set-level structural priors for semi-supervised hyperbolic hierarchical clustering.
result Improves label consistency and similarity-based tree quality over baselines.
Bayesian model updates data streams with hierarchical priors.
problem Continuous model updating and adapt to changes in data distribution.
method Non-conjugate hierarchical priors and variational inference.
result Validated on real data sets, demonstrating adaptability.
Bayesian models use hyperparameters to indirectly assign priors, and this work shows how these priors can be derived from maximum entropy principles.
problem Understanding the assumptions and dependencies in Bayesian hierarchical models.
method Demonstrates how canonical distributions and maximum entropy principles can be used to derive marginal priors in hierarchical models.
result Marginal priors in hierarchical models derived from maximum entropy principles have different constraints compared to the original priors.
A new method learns hierarchical EBM models with diffusion schemes.
problem Challenges in learning EBM models with multi-modal distributions.
method Proposes a diffusion probabilistic scheme to learn EBM models in hierarchical latent spaces.
result Demonstrates superior performance on various tasks with diffusion-learned EBM.
A hierarchical segmentation method for images with weak supervision.
problem Weakly supervised image segmentation.
method Flexible hierarchical segmentation considering prior spatial information.
result Enhanced segmentation of regions of interest while preserving important structures.
Hierarchical beta process has found interesting applications in recent years. In this paper we present a modified hierarchical beta process prior with applications to hierarchical modeling of multiple data sources. The novel use of the prior over a hierarchical factor model allows factors to be shared across different …
New MIF architecture improves posterior approximations in Bayesian models.
problem Challenges in variational inference for complex hierarchical models.
method Combines VIP and autoregressive flow with prior information and hierarchical ordering.
result Empirically, MIF delivers tighter posterior approximations and state-of-the-art performance.
Proposes a new VAE model with hierarchical nonparametric priors for better data representation.
problem Limited flexibility of standard VAE latent representations.
method Combines tree-structured Bayesian nonparametric priors with VAEs for joint learning of neural parameters and priors.
result Discover highly interpretable activity hierarchies and improved clustering accuracy.
This paper proves the necessity and effectiveness of learning the prior in VAEs.
problem Aggregated posterior may not match unit Gaussian prior, leading to poor variational inference.
method Proves necessity and effectiveness of learning the prior, analyzes why it's needed, and proposes hypothesis.
result Learning the prior can improve reconstruction loss and achieve comparable test NLL to deep hierarchical VAEs.
New method simplifies Bayesian inference for multi-Dirichlet priors.
problem Inference for models with hierarchical Multi-Dirichlet priors is tricky.
method Auxiliary variable scheme simplifies joint distribution of model parameters.
result Efficient inference schemes derived using the auxiliary variable scheme.
Two new estimators improve VAE training for hierarchical and prior parameters.
problem Efficient gradient estimation for VAEs with hierarchical and prior parameters.
method Developed two generalizations of Doubly-Reparameterized Gradient Estimators (DReGs) for VAEs.
result Improved training of conditional and hierarchical VAEs on image modeling tasks.
New Bayesian method for joint sparse parameter inference.
problem Inference of jointly sparse parameter vectors from multiple measurements.
method Hierarchical Bayesian learning with joint sparsity-promoting priors.
result New algorithms consistently outperform existing methods in numerical experiments.
RG-Flow combines RG and sparse priors for hierarchical image disentanglement.
problem Disentangling and manipulating image representations at different scales.
method Hierarchical flow model using RG and sparse prior distributions.
result RG-Flow enables semantic manipulation and style mixing at different image scales.
Proposes a method to incorporate prior domain knowledge into hierarchical clustering.
problem Hierarchical clustering results depend on similarity measures and algorithm choices.
method Uses ultrametric distance function to encode external ontological information and adds it as a penalty term to the original pairwise distance.
result Popular linkage-based algorithms can faithfully recover the encoded structure.
A new method for Bayesian neural networks using probabilistic backpropagation.
problem Approximating posterior distributions in Bayesian neural networks.
method Variational Expectation Propagation (VEP) with probabilistic backpropagation.
result Efficient algorithm for approximate integration over posterior distributions.
Unified Bayesian framework for PTA data analysis tackles hierarchical model issues.
problem Hierarchical Bayesian modeling challenges in PTA data analysis.
method Reparameterization strategy using Normalizing Flows (NFs) and i-nessai nested sampler.
result Improved statistical robustness and computational efficiency in PTA analysis.
We propose a novel approach for nonlinear regression using a two-layer neural network (NN) model structure with sparsity-favoring hierarchical priors on the network weights. We present an expectation propagation (EP) approach for approximate integration over the posterior distribution of the weights, the hierarchical s…
Bayesian algorithm improves word representations using semantic taxonomy.
problem Improving word representations in semantic taxonomy.
method Bayesian Hierarchical Words Representation (BHWR) learning algorithm combining Variational Bayes and semantic taxonomy modeling.
result BHWR produces better representations for rare words.
HyperBO+ pre-trains a universal prior for Bayesian optimization across different domains.
problem Bayesian optimization requires domain-specific priors, limiting its applicability.
method Two-step pre-training method for hierarchical Gaussian processes.
result HyperBO+ achieves lower regrets on unseen search spaces.
This paper introduces hierarchical Gaussian process priors for neural networks to capture weight correlations and inductive biases.
problem Capturing weight correlations and inductive biases in neural networks.
method Hierarchical Gaussian process priors with unit embeddings and input-dependent kernels.
result Hierarchical Gaussian process priors provide competitive predictive performance and desirable uncertainty estimates.
Hierarchical IBP model for Bayesian neural networks in continual learning.
problem Resource allocation in continual learning with dynamic network complexity.
method Indian Buffet process (IBP) and Hierarchical-IBP (H-IBP) priors for structure learning, online variational inference with reparameterization.
result Our model effectively learns the number of weights in each layer, overcoming overfitting and underfitting.
Existing methods for sparse channel estimation typically provide an estimate computed as the solution maximizing an objective function defined as the sum of the log-likelihood function and a penalization term proportional to the l1-norm of the parameter of interest. However, other penalization terms have proven to have…
Bayes-Factor-VAE models improve disentanglement of latent factors in data.
problem Disentangling latent factors in data using standard Gaussian priors is suboptimal.
method Introduced hierarchical Bayesian deep auto-encoder models with hyper-priors on latent variances.
result Bayes-Factor-VAEs outperform existing methods in latent disentanglement.
DS2CF-Net learns hierarchical representations with deep coupled factorization and enriched prior.
problem Learning deep hierarchical representations from data.
method Dual-constrained Deep Semi-Supervised Coupled Factorization Network (DS2CF-Net) with enriched prior.
result DS2CF-Net achieves state-of-the-art performance in representation learning and clustering.
Improved deep hierarchical VAE with diffusion-based VampPrior.
problem Latent variable generative modeling challenges.
method Hierarchical VAE with amortized diffusion-based VampPrior.
result Better performance with fewer parameters and improved stability.
Bayesian model predicts fashion size recommendations and returns.
problem Predicting optimal fashion sizes and handling returns efficiently.
method Hierarchical Bayesian model for size and return events.
result Model incorporates domain expertise and article characteristics.
BoRA finetunes multi-task LLMs by sharing information through hierarchical priors.
problem Limited data for some tasks in multi-task LLMs.
method Bayesian hierarchical low-rank adaption.
result BoRA outperforms individual and unified model approaches.
Paper proposes VampPrior to improve VAEs.
problem Improving variational auto-encoders (VAEs) with a new prior.
method Integrates a Variational Mixture of Posteriors (VampPrior) into VAEs.
result The hierarchical VampPrior architecture learns better models and avoids latent dimension issues.
A new model separates persistence and transition priors in HDP-HMM.
problem Limitation of sticky HDP-HMM in expressing different persistence strengths.
method Developed a disentangled sticky HDP-HMM (DS-HDP-HMM) with novel Gibbs sampling algorithms.
result DS-HDP-HMM outperforms sticky HDP-HMM and HDP-HMM on synthetic and real data.
The LORACs prior improves latent representation interpretability in VAEs.
problem Learning interpretable latent representations in VAEs.
method Flexible Bayesian nonparametric hierarchical clustering prior based on TMC for VAEs.
result Improved interpretability and practical performance of latent space.
New algorithm reduces regret in multi-armed bandit problems with Gaussian rewards.
problem Optimizing decisions in multi-armed bandit problems with Gaussian rewards.
method Proposed TSCG and UTSCG algorithms using Thompson Sampling with Gaussian prior.
result Achieved lower regret bounds for optimal arm selection.
New model learns hierarchical features from generative models.
problem Generative models struggle with hierarchical feature learning.
method Proposed an alternative architecture to overcome limitations.
result Model learns interpretable, disentangled hierarchical features.
The paper tackles hierarchical clustering with structural constraints, providing approximation guarantees and improving upon current techniques.
problem Exploiting prior information in hierarchical clustering for real-world applications.
method Top-down algorithms with provable approximation guarantees, using optimization viewpoint and constraint-based regularization.
result Improved solutions for hierarchical clustering with conflicting prior information.
Paper proposes a method for estimating complex low-rank matrices from phase-only measurements.
problem Estimating complex low-rank matrices from magnitude-only measurements.
method A hierarchical prior model with a Gaussian-Wishart distribution is used to promote low-rankness. A variational EM algorithm is developed to solve the problem.
result The proposed method is less sensitive to initialization and performs well with random initialization.
Federated learning is viewed as a hierarchical latent variable model for new algorithm development.
problem Training models privately across multiple clients while maintaining privacy and efficiency.
method Viewing federated learning as a hierarchical latent variable model and applying Expectation-Maximization (EM) algorithm.
result Proposes FedSparse, a federated learning algorithm that promotes sparsity and reduces communication and inference costs.
Proposes a hierarchical RL method with abductive planning for complex tasks.
problem Challenges in applying RL to complex real-life problems.
method Hierarchical reinforcement learning with abductive planning.
result Significantly improves learning efficiency in unknown state spaces.
New model predicts stochastic dynamics with hidden variables.
problem Predicting state transitions in stochastic dynamical systems.
method Hierarchical Bayesian linear regression with local features and variational EM algorithm.
result Parsimonious model structures and fast, accurate predictions.
Transforms hierarchical model parameters to decouple dependencies and improve inference.
problem Problematic dependencies between hierarchical model parameters.
method Transformation of model parameters using multivariate distributional transform.
result Decouples transformed parameters a priori, leading to faster inference.
Improved VAEs by training a contrastive prior to match posterior.
problem Prior hole problem in VAEs, leading to poor image generation.
method Introduced a contrastive energy-based prior and trained it using noise contrastive estimation.
result Significant improvement in VAE generative performance on various datasets.
Study uses healthcare claims data to identify Covid-19 risk factors without prior selection.
problem Identify risk factors for severe Covid-19 cases.
method Fine-grained hierarchical information from medical classification systems used to analyze over 33,000 covariates.
result Method has better predictive ability than pre-specified morbidity groups.
This paper improves neural network explanations by quantifying and visualizing semantic compositions.
problem Improving neural network explanations for natural language processing tasks.
method Proposes a formal way to quantify word and phrase importance, introduces SCD and SOC algorithms.
result Our algorithms outperform prior methods in explaining neural network predictions.
New model tackles region-sparse regression with hierarchical Gaussian process.
problem Sparse and dependent parameter vectors in regression settings.
method Hierarchical model with transformed Gaussian process and structured Fourier coefficients.
result Substantial improvements over comparable methods in simulated and real datasets.
MSOL learns hierarchical policies for multitask tasks with soft options.
problem Training hierarchical policies for multiple tasks with stability and flexibility.
method MSOL uses separate variational posteriors for each task, regularized by a shared prior, to avoid instabilities and fine-tune options for new tasks.
result MSOL significantly outperforms hierarchical and flat transfer-learning baselines.