Boxhead dataset tests autoencoder disentanglement in hierarchical data.
problem Evaluate disentanglement in hierarchical data.
method Introduced Boxhead dataset with hierarchically structured factors, evaluated autoencoder models.
result Hierarchical models outperform single-layer VAEs in disentangling factors.
A hierarchical clustering algorithm for data clouds without structure assumptions.
problem Exploring data clouds without making structure assumptions.
method Hierarchical topological clustering algorithm that infers persistence of outliers and clusters of arbitrary shape from data hierarchy.
result The algorithm can provide meaningful clusters in complex datasets.
New combinatorial structure for hierarchically hyperbolic spaces.
problem Constructing new hierarchically hyperbolic spaces.
method Combinatorial hierarchical hyperbolicity criterion to construct and clarify HHS structures.
result HHSs admit a combinatorial structure, clarifying the application of the combinatorial HHS criterion.
Researchers identify latent variables and causal structures from nonlinear hierarchical models.
problem Challenging task of identifying latent variables and causal structures from observational data, especially when relationships are nonlinear.
method Investigated nonlinear latent hierarchical causal models, developed identification criterion, and constructed an estimation procedure.
result Identifiability of causal structures and latent variables achieved under mild assumptions.
Extends clustering method to cost-based hierarchies.
problem Guaranteeing near-optimality in hierarchical clustering.
method Optimization-based Sublevel Set method extended to cost-based hierarchies.
result Ensures clustering is nearly optimal without distributional assumptions.
Study on kernels for optimizing functions with hierarchical variables.
problem Optimizing functions with hierarchical variables requires efficient surrogate models.
method Investigate and propose alternative kernels for hierarchical variables in surrogate models.
result Different kernels and assumptions affect model quality and search performance.
Hierarchical Federated Learning bounds generalize using Wasserstein distance.
problem Bounding generalization error in Federated Learning with hierarchical sampling.
method Introduced a hierarchical sampling framework and derived generalization bounds using Wasserstein distance.
result Recover and strictly imply existing CMI bounds for bounded losses.
New model addresses instability in hierarchical clustering of social networks.
problem Instability in existing hierarchical clustering algorithms for social networks.
method Introduce T \mathbb{T} T -Stochastic Graphs, a probabilistic model that relaxes ultrametric assumptions. result Prove spectral approach combining Neighbor-Joining is statistically consistent.
Develops a new method to analyze hierarchical data from multiple perspectives.
problem Current multi-view and hierarchical methods are limited and do not apply to graphical data.
method Generalizes Treelet Transform to Multi-View Treelet Transform (MVTT).
result MVTT captures hierarchical structure in multi-view settings.
This work analyzes Gibbs samplers for Bayesian hierarchical models without dimensionality constraints.
problem Analyzing convergence properties of Gibbs samplers for Bayesian hierarchical models.
method Using Bayesian asymptotics and total variation mixing times, the study provides dimension-free convergence results.
result Dimension-free convergence results for Gibbs samplers targeting hierarchical models under random data-generating assumptions.
Efficiently clusters data with weak assumptions, robust to contamination.
problem General-shaped clustering under weak parametric assumptions with data contamination.
method Two-step hybrid robust clustering algorithm combining trimmed k-means and hierarchical agglomeration.
result Outperforms state-of-the-art methods in various applications.
The study shows how quotients of mapping class groups are hierarchically hyperbolic.
problem Understanding the hierarchical hyperbolicity of mapping class groups and their quotients.
method A combinatorial criterion for hierarchical hyperbolicity applied to mapping class groups.
result Quotients of mapping class groups by large powers of Dehn twists are hierarchically hyperbolic.
Reduces high granularity and dimensionality in hierarchical categorical variables.
problem Overfitting and estimation issues in predictive models due to high granularity and dimensionality.
method Entity embedding and top-down clustering algorithm to reduce granularity and dimensionality.
result The reduced hierarchy improves model fit and complexity balance.
Bayesian model for sparse regression with spatial-temporal structure.
problem Sparse linear regression with spatio-temporal constraints.
method Hierarchical Gaussian process prior and Expectation Propagation algorithm.
result Model successfully applied to real data.
We develop correlated random measures, random measures where the atom weights can exhibit a flexible pattern of dependence, and use them to develop powerful hierarchical Bayesian nonparametric models. Hierarchical Bayesian nonparametric models are usually built from completely random measures, a Poisson-process based c…
DEHRL extends HRL to handle multiple levels with diverse subpolicies.
problem Handling multiple levels of hierarchical reinforcement learning with diverse subpolicies.
method Extensible and scalable framework built levelwise, focusing on diversity of subpolicies.
result DEHRL outperforms state-of-the-art baselines in multiple domains.
Using data from a sample of 28 representatives countries, we propose a classification of currency crises consequences based on the ultrametric analysis of the real exchange rate movements time series, without any further assumption. By using the matrix of synchronous linear correlation coefficients and the appropriate …
The ability to adequately model risks is crucial for insurance companies. The method of "Copula-based hierarchical risk aggregation" by Arbenz et al. offers a flexible way in doing so and has attracted much attention recently. We briefly introduce the aggregation tree model as well as the sampling algorithm proposed by…
Proposes HOT method for robust multi-view learning.
problem Inability of traditional methods to handle unaligned and non-distributionally aligned views.
method Hierarchical optimal transport (HOT) method that penalizes sliced Wasserstein distances between different views.
result HOT method achieves robust performance on both synthetic and real-world tasks.
Proposes a new learning framework for scalable image classification.
problem Scalability issues in CNN-based image classifiers for large number of classes.
method Combines hierarchical classification and auxiliary learning to address scalability issues.
result Reduces classification errors by up to 3.56% on CIFAR-10 dataset.
HCRNN uses hierarchical contexts to improve recommendation models.
problem Challenges in modeling user interest transitions and drifts in recommendation systems.
method Introduces HCRNN with three hierarchical contexts (global, local, temporary) and a hierarchical context-based gate structure.
result HCRNN outperformed other models in sequential recommendation tasks.
HGNet improves GNNs' ability to handle long-range interactions in graphs.
problem Insufficiency of GNNs in capturing long-range interactions.
method Introduces hierarchical message passing models with multi-resolution graph representations.
result HGNet outperforms conventional GNNs in molecular property prediction.
MLCC clusters data at multiple significance levels, detecting anomalies without distributional assumptions.
problem Clustering and anomaly detection in data with unknown distributions.
method Hierarchical, conformal prediction-based clustering.
result MLCC automatically selects cluster number and detects anomalies robustly.
Paper learns latent and hierarchical structures in CDMs from data.
problem Jointly learning latent and hierarchical structures in CDMs from observed data.
method Penalized likelihood approach for selecting attributes and estimating structures; EM and latent structure recovery algorithms.
result Good performance demonstrated by simulation and real data applications.
New framework for domain adaptation using hierarchical optimal transport.
problem Improving domain adaptation when source and target data distributions differ.
method Proposes a new theoretical framework and hierarchical Wasserstein distance.
result Provides more explicit generalization bounds and aligns specific structures for successful adaptation.
Paper tackles online hierarchical clustering, offering efficient algorithms with good quality clusters.
problem Offline hierarchical clustering algorithms require full dataset, limiting their use on large datasets.
method Proposes two online algorithms (OTD and OHAC) to optimize Moseley and Wang revenue function.
result OTD achieves 1/3-approximation to MW revenue under data separation assumption.
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.
CoHiRF extends clustering methods to handle high-dimensional data efficiently.
problem Scalability limits of existing clustering methods.
method Hierarchical consensus framework operating on label assignments.
result Improves robustness and scalability to high-dimensional noise.
Study improves forecasting of aggregated curves in electricity markets.
problem Improving accuracy in predicting aggregated curves like demand and supply in electricity markets.
method Exploits hierarchical structure of aggregated curves, uses reconciliation methods (bottom-up, top-down, linear optimal, aggregated-down).
result Hierarchical reconciliation methods can significantly improve forecast accuracy of aggregated curves.
Hierarchical Partial-Order Models for Ranking
problem Rank aggregation combining ordered lists
method Hierarchical partial-order models
result Bayesian inference for latent poset hierarchy
New model infers causal relationships from spatio-temporal data, even with unobserved confounders.
problem Challenges in inferring causal relationships from spatio-temporal data due to unobserved confounders.
method Spatio-Temporal Hierarchical Causal Models (ST-HCMs) that extend hierarchical causal modeling to the spatio-temporal domain, using the Spatio-Temporal Collapse Theorem.
result Validated the effectiveness of ST-HCMs on both synthetic and real-world datasets, demonstrating robust causal inference in complex dynamic systems.
GANs can learn hierarchical distributions in real-world images efficiently.
problem Understanding and efficiently learning complex, real-world distributions with GANs.
method Formally studying how GANs can learn hierarchically generated distributions close to real-life image distributions using SGDA.
result Training GANs via SGDA can efficiently learn distributions with a 'forward super-resolution' structure, both in sample and time complexities.
HierLPR ranks labels hierarchically for multi-label classification, optimizing a new eAUC metric.
problem Hierarchical multi-label classification with emphasis on first call accuracy.
method Introduces HierLPR algorithm optimizing eAUC metric under tree constraint.
result HierLPR outperforms other methods in early precision-recall curve stages.
The paper develops a theory for clustering graphs sampled from a graphon model.
problem Clustering graphs sampled from a graphon model.
method Define clustering correctness, provide sufficient conditions for consistency, and develop an explicit algorithm.
result An explicit algorithm for graph clustering is provided and shown to be statistically consistent.
Improves RL planning by proposing sub-goals hierarchically.
problem Sequential planning assumption in RL.
method Divide-and-Conquer Monte Carlo Tree Search (DC-MCTS).
result Improves navigation and control tasks.
New method detects concept drifts with fewer labels.
problem Real-world data drifts over time, affecting model performance.
method Hierarchical Hypothesis Testing with Request-and-Reverify strategy.
result Significant reduction in label requests with improved performance.
A hierarchical community detection method using recursive partitioning.
problem Finding interpretable and accurate community structures in networks.
method Top-down recursive partitioning starting with spectral clustering.
result The algorithm correctly recovers community trees under mild assumptions.
PERCH efficiently clusters large datasets with many clusters.
problem Clustering large datasets with many clusters.
method Online hierarchical algorithm that routes new data points to tree leaves and performs tree rotations for enhanced purity and balancedness.
result PERCH constructs more accurate trees than other algorithms and scales well with both N and K.
Paper improves SOMs for non-Euclidean data modeling.
problem Traditional SOMs assume Euclidean data, limiting their applicability.
method Introduces topology-related extensions to traditional SOM algorithm.
result Improves SOMs for non-Euclidean data, enhancing data modeling.
New methods tackle complex inverse problems with scalable optimization-based MCMC.
problem Estimating high-dimensional model parameters and hyperparameters in nonlinear hierarchical statistical inverse problems.
method Optimization-based Markov chain Monte Carlo (MCMC) methods using RTO and pseudo-marginal MCMC.
result Efficient sampling tools for hierarchical Bayesian inversion with robust performance to model parameter dimensions.
SCAN learns hierarchical visual concepts from unsupervised data.
problem Discovering coherent rules in natural world visual diversity.
method SCAN learns concepts through fast symbol association and disentangled visual primitives.
result SCAN generates diverse images from symbolic descriptions and manipulates visual concepts hierarchically.
New algorithm tracks changes in infinite action space rewards.
problem Non-stationary Lipschitz bandits with infinite actions.
method Adaptive tracking of significant shifts using hierarchical discretization.
result Achieves minimax-optimal dynamic regret bound of O ~ ( i l d e L 1 / 3 T 2 / 3 ) \mathcal{\widetilde{O}}( ilde{L}^{1/3}T^{2/3}) O ( i l d e L 1/3 T 2/3 ) . Expands causal clustering framework with hierarchical and density-based methods.
problem Identifying heterogeneous treatment effects in unknown subgroup structure.
method Integrates hierarchical and density-based clustering algorithms into causal k-means clustering.
result Plug-in estimators for causal clustering are simple and readily implementable.
Optimum-statistical collaboration improves black-box optimization efficiency.
problem Improving black-box optimization efficiency through better statistical collaboration.
method Introducing optimum-statistical collaboration framework for hierarchical bandits-based optimization.
result Demonstrated improved regret bounds and better performance in experiments.
HIP-GP improves GP inference for inter-domain observations with millions of inducing points.
problem Inference for Gaussian Processes across different domains.
method Hierarchical inducing point Gaussian process with grid structure and stationary kernel assumption.
result Improved approximation accuracy through increased number of inducing points.
A new method for accurately reconstructing signals without knowing the kernel or signal regularity.
problem Recovering signals from noisy measurements without prior knowledge of the convolution kernel or signal regularity.
method Parametrizing the convolution kernel and prior length-scales, jointly estimated in the inversion procedure.
result Accurate reconstructions of signals with varying regularity and unknown kernel size.
HEBAE improves VAEs by adaptively balancing reconstruction and regularization.
problem Posterior collapse in VAEs leading to over-regularization and poor latent encoding.
method Hierarchical Empirical Bayes approach to probabilistic generative models.
result HEBAE generates higher quality samples with better FID scores.
New model improves cancer screening prediction accuracy.
problem Modeling disease progression with heterogeneous populations and irregular data.
method Hierarchical Hidden Markov Jump Processes with piece-wise stationary transitions and scalable EM algorithm.
result Model outperforms state-of-the-art models in prediction accuracy and generating Kaplan-Meier estimators.