Method estimates group structure in panel data using variance information.
problem Estimating group structure in panel data with unknown groups.
method Proposes a method to estimate unobserved groupings for panel data models using variance information.
result Superior performance compared to existing methods in simulations and empirical applications.
Geometric analysis on diffeomorphism groups for fluid dynamics and information geometry.
problem Geometric analysis of fluid flows and optimal mass transport.
method Review of metrics and topology on diffeomorphism groups.
result Introduction of new metrics and topology for diffeomorphism groups.
Normal distribution manifolds play essential roles in the theory of information geometry, so do holonomy groups in classification of Riemannian manifolds. After some necessary preliminaries on information geometry and holonomy groups, it is presented that the corresponding Riemannian holonomy group of the d-dimension…
In this work, we study generalized entropies and information geometry in a group-theoretical framework. We explore the conditions that ensure the existence of some natural properties and at the same time of a group-theoretical structure for a large class of entropies. In addition, a method for defining new entropies, u…
Develops theory of homogeneous statistical manifolds and classifies Lie groups.
problem Understanding statistical manifolds and Lie groups.
method Constructs examples and classifies Lie groups using information geometry.
result Explicit examples of homogeneous statistical manifolds of low dimension constructed.
Feature noise causes loss discrepancies across groups even with equal data.
problem Loss discrepancies observed in learning procedures across different groups.
method Characterized the effect of feature noise on loss discrepancy in linear regression.
result Feature noise leads to loss discrepancy even when groups have equal data.
Singing voice separation attempts to separate the vocal and instrumental parts of a music recording, which is a fundamental problem in music information retrieval. Recent work on singing voice separation has shown that the low-rank representation and informed separation approaches are both able to improve separation qu…
Bayesian method for feature selection with grouping info using expectation propagation.
problem Feature selection with grouping info and sparsity constraints.
method Sparse-group Bayesian feature selection using expectation propagation.
result Our method outperforms existing methods in terms of feature selection accuracy and computational efficiency.
Cone structures in quantum field theory linked to information geometry.
problem Understanding geometric structures in quantum field theory.
method Analyzing invariant cones under modular automorphism groups and their relation to Wishart laws.
result Explicit connection between CAH cones and Wishart laws.
Calibrating classifiers reduces grouping loss using sufficiency criteria.
problem Grouping loss in probabilistic classifier calibration is often overlooked.
method Revisited Langford & Zadrozny's probing reduction approach and introduced Brier curves.
result The probing reduction approach reduces grouping loss and supports sufficient calibration.
Paper tackles group robustness with partially labeled data.
problem Learning invariant representations from datasets with spurious correlations.
method Constructs a constraint set and derives a high probability bound for group assignment. Proposes an optimization algorithm for worst-off group assignments.
result Improvements in minority group's performance while preserving overall accuracy.
Exclusive Group Lasso improves feature selection in correlated biological data.
problem Correlated features hinder Lasso performance in biological classification problems.
method Proposes and solves the exclusive group Lasso, combining stability selection and random group allocation.
result Exclusive Group Lasso outperforms Lasso in comprehensive selection of informative features.
Sparse mapping has been a key methodology in many high-dimensional scientific problems. When multiple tasks share the set of relevant features, learning them jointly in a group drastically improves the quality of relevant feature selection. However, in practice this technique is used limitedly since such grouping infor…
MICO uses mutual information co-training to improve selective search efficiency.
problem Efficiently search and route unseen queries in large-scale search systems.
method Mutual Information Co-training framework for selective search with minimal supervision.
result Significantly improves performance on multiple metrics of selective search.
Williams and Beer (2010) proposed a nonnegative mutual information decomposition, based on the construction of redundancy lattices, which allows separating the information that a set of variables contains about a target variable into nonnegative components interpretable as the unique information of some variables not p…
This paper introduces efficient approximations for fairness criteria in regression models.
problem Measuring fairness in real-valued outcomes (regression settings) is computationally challenging.
method Fast approximations of mutual information for independence, separation, and sufficiency fairness criteria.
result The method achieves state-of-the-art accuracy/fairness tradeoffs in real-world datasets.
We describe the second integral cohomology group of a surface bundle as the group of Chern classes of fiberwise holomorphic complex line bundles and use this to obtain information on this group.
Develops a method to ensure fairness across multiple sensitive attributes in machine learning.
problem Ensuring fairness among demographic groups formed by multiple sensitive attributes.
method Formulates intersectional fairness as a mutual information minimization problem and proposes a generic end-to-end algorithmic framework.
result Demonstrates effective debiasing of classification results with minimal impact to accuracy.
We show that the last few components in principal component analysis of the correlation matrix of a group of stocks may contain useful financial information by identifying highly correlated pairs or larger groups of stocks. The results of this type of analysis can easily be included in the information an investor uses …
New metrics for information geometry and machine learning from Lie groups.
problem Traditional mean methods in data science and machine learning.
method Cartan-Schouten metrics on Lie groups.
result Cartan-Schouten metrics offer advantages over traditional means.
GWIB improves counterfactual regression by balancing latent distributions and reducing selection bias.
problem Selection bias between control and treatment groups negatively impacts counterfactual regression performance.
method GWIB uses Gromov-Wasserstein information bottleneck to maximize mutual information between covariates and outcomes while penalizing kernelized mutual information between latent representations and covariates.
result GWIB consistently outperforms state-of-the-art CFR methods in ITE estimation tasks.
DADI framework dynamically discovers fair information using reinforcement learning.
problem Discovering fair information from third-party features with unknown objectives.
method Adversarial reinforcement learning agent that balances accuracy and fairness.
result Achieves group fairness by rewarding the agent with the adversary's loss.
This paper studies moduli spaces of statistical structures on Lie groups.
problem Understanding statistical structures on Lie groups.
method Introduced and studied moduli spaces for left-invariant statistical structures on Lie groups.
result Moduli spaces of left-invariant Riemannian metrics are singletons for certain Lie groups.
Proposes a group-splicing algorithm for efficient BSGS in high-dimensional settings.
problem Efficiently selecting a small part of non-overlapping groups for best interpretability in high-dimensional settings.
method Iteratively detects relevant groups and excludes irrelevant ones using a novel group information criterion.
result Certifiable polynomial-time algorithm for identifying the optimal subset of groups with high probability.
Generalizes underlap coefficient for multivariate group separation.
problem Quantifying distributional separation across groups in statistical learning.
method Generalizes underlap coefficient (UNL) to multivariate settings, studies its relationship with Bayes risk and mutual information, proposes an efficient importance sampling estimator.
result UNL as a measure of dependence between group labels and variables of interest, interpretable measure of partition-covariate dependence in clustering.
ComEx protocol reduces communication costs in cooperative bandits.
problem Minimizing communication costs in cooperative bandits while maintaining optimal performance.
method Developed ComEx protocol to reduce communication from Θ(T) to O(logT) messages. result Achieves state-of-the-art performance with significantly reduced communication cost.
This work improves disentanglement by preventing style variables from encoding content-related features.
problem Disentanglement of content and style in data representations using Variational Autoencoders.
method Adversarial training with mutual information minimization to prevent content information leakage in style representations.
result The method efficiently separates content and style related attributes and generalizes to unseen data.
Artin groups have a special structure that helps prove a complex mathematical conjecture.
problem Proving the Farrell-Jones isomorphism conjecture for Artin groups.
method Identifying an inductive structure in Artin groups and applying it to the conjecture.
result The Farrell-Jones isomorphism conjecture is proven for certain Artin groups.
The paper proposes a method to improve fairness in classification without using sensitive features directly.
problem Balancing accuracy and fairness in automated decision-making systems.
method Combining Multitask Learning with fairness constraints to train group-specific classifiers.
result The method achieves substantial improvements in both accuracy and fairness on real datasets.
We find explicit subdivision rules for all special cubulated groups. A subdivision rule for a group produces a sequence of tilings on a sphere which encode all quasi-isometric information for a group. We show how these tilings detect properties such as growth, ends, divergence, etc. We include figures of several worked…
Algorithm samples fair rankings to ensure individual fairness while maintaining group fairness.
problem Fair ranking tasks with group fairness constraints and uncertainty in item utilities.
method Efficient algorithm that samples rankings from an individually-fair distribution ensuring group fairness.
result Expected utility of output ranking is at least α times optimal fair solution, where α depends on utilities and constraints.
Study quantifies information flow in neural networks using relative entropy and RG analogy.
problem Quantifying information flow in deep neural networks.
method Explicit computation of relative entropy in Ising models and feedforward neural networks.
result Monotonic increase of relative entropy to an asymptotic value, confirming connection to c-theorem.
Much is known about random right-angled Coxeter groups (i.e., right-angled Coxeter groups whose defining graphs are random graphs under the Erdös-Rényi model). In this paper, we extend this model to study random general Coxeter groups and give some results about random Coxeter groups, including some information about t…
We propose a new problem formulation which is similar to, but more informative than, the binary multiple-instance learning problem. In this setting, we are given groups of instances (described by feature vectors) along with estimates of the fraction of positively-labeled instances per group. The task is to learn an ins…
Optimizes group testing for COVID-19 to reduce test numbers.
problem Minimizing tests for accurate infection detection.
method Bayesian approach with genetic algorithms and sub-modularity.
result Greedy-adaptive method provides theoretical guarantees.
A new method embeds labels and group information for efficient multi-label classification.
problem Efficient multi-label classification with label sparsity and group structure.
method Identifies label groups, embeds labels and features in a low-dimensional space preserving sparsity and group structure.
result Our method outperforms state-of-the-art algorithms on benchmark datasets.
New method solves group synchronization with cycle-edge message passing.
problem Solving group synchronization with adversarial or uniform corruption and small noise.
method Cycle-edge message passing procedure using cycle consistency information.
result Exact recovery and linear convergence guarantees under adversarial corruption.
Suggests stopping criteria for feature selection using mutual information.
problem Automatic determination of optimal feature subset size and stopping criterion.
method Monitoring conditional mutual information (CMI) among groups of variables using Renyi's α-entropy.
result Easy to implement stopping criteria for feature selection.
Study on convergence rates of degenerate SDEs using Fisher information and generalized Bochner's formula.
problem Analysis of dynamical behaviors of degenerate stochastic differential equations.
method Use of Fisher information as Lyapunov functional, generalized Gamma calculus, and generalized Bochner's formula.
result Derivation of convergence rate conditions and examples in specific sub-Riemannian structures.
For a link L in the 3-sphere and for a prime p, we express the p-primary information on the first homology group of pm-fold branched covers of L in terms of its p-adic Milnor higher linking invariants, using the completed Alexander module of the pro-p completion of the link group of L.
We present a Bayesian nonparametric framework for multilevel clustering which utilizes group-level context information to simultaneously discover low-dimensional structures of the group contents and partitions groups into clusters. Using the Dirichlet process as the building block, our model constructs a product base-m…
There is growing evidence regarding the importance of spike timing in neural information processing, with even a small number of spikes carrying information, but computational models lag significantly behind those for rate coding. Experimental evidence on neuronal behavior is consistent with the dynamical and state dep…
Geometric framework for Newton's equations on diffeomorphism groups.
problem Modeling fluid dynamics and related systems on geometric spaces.
method Geodesic approach and infinite-dimensional information geometry.
result Unified framework for various fluid dynamics equations.
Study examines BTZ black hole using information geometry.
problem Understanding the BTZ black hole mechanism.
method Information geometry, Hessian potential, Legendre transformation.
result Exact BTZ metric and entanglement entropy derived.
Approximate inference via information projection has been recently introduced as a general-purpose approach for efficient probabilistic inference given sparse variables. This manuscript goes beyond classical sparsity by proposing efficient algorithms for approximate inference via information projection that are applica…
An entirely new and independent enumeration of the crystallographic space groups is given, based on obtaining the groups as fibrations over the plane crystallographic groups, when this is possible. For the 35 ``irreducible'' groups for which it is not, an independent method is used that has the advantage of elucidating…
Paper proposes TPathMine model for more accurate user attribute prediction.
problem Predicting user attributes from click data in heterogeneous networks.
method HetPathMine model with meta-path weights optimized for user emotional preferences.
result TPathMine model achieves higher accuracy in user attribute prediction.
DHOG improves unsupervised clustering accuracy on image benchmarks.
problem Local optima in mutual information maximisation lead to suboptimal representations.
method Deep hierarchical object grouping (DHOG) computes multiple discrete representations in a hierarchical order.
result DHOG achieves new state-of-the-art results on three main benchmarks.