This paper solves the intractability barrier in non-parametric information geometry by introducing a novel framework.
problem The intractability barrier in non-parametric information geometry due to the Fisher-Rao metric being a functional.
method Introducing an Orthogonal Decomposition of the Tangent Space and deriving the Covariate Fisher Information Matrix (cFIM).
result Established a rigorous foundation for the G-entropy and provided fundamental limits of variance for semi-parametric estimators.
This paper solves the normalizability crisis in sequential inference by introducing bounded information geometry.
problem Structural failure in standard sequential inference architectures when dealing with extreme outliers.
method Non-parametric field actions and bounded information geometry to truncate infinite tails of spatial distributions.
result Empirical benchmarks across three domains show robust estimation without infinite-tailed distributional assumptions.
We consider the problems of clustering, classification, and visualization of high-dimensional data when no straightforward Euclidean representation exists. Typically, these tasks are performed by first reducing the high-dimensional data to some lower dimensional Euclidean space, as many manifold learning methods have b…
Estimates non-parametric logistic model using case-control data and external summary info.
problem Imbalanced binary data in case-control studies.
method Two-step estimation procedure with deep neural network for functional approximation.
result Proposed estimator achieves optimal convergence rate in non-parametric regression.
We propose a method for learning Markov network structures for continuous data without invoking any assumptions about the distribution of the variables. The method makes use of previous work on a non-parametric estimator for mutual information which is used to create a non-parametric test for multivariate conditional i…
The paper develops a theory for identifying the best arm in non-parametric multi-armed bandits with a fixed budget.
problem Identifying the best arm in non-parametric multi-armed bandits with a limited number of trials.
method The paper proposes upper and lower bounds on the average log-probability of misidentification using information-theoretic quantities and a refined analysis of the successive-rejects strategy.
result The paper provides new upper and lower bounds on the average log-probability of misidentification, which generalize existing bounds.
Estimates classifier errors without ground truth using algebraic geometry.
problem Lack of ground truth in real-world production systems.
method Non-parametric estimation using algebraic geometry to solve the self-assessment problem.
result Accuracy estimators are better than one part in a hundred.
Study uses non-parametric method to analyze EU ETS price determinants.
problem Understanding price determinants of EU ETS to inform policy.
method Non-parametric measure (Information Imbalance) to study variables.
result Commodity variables are most informative in Phase 3, while financial variables become more important in Phase 4.
DPPS uses DP priors for Bayesian non-parametric multi-arm bandits.
problem Optimizing multi-arm bandit environments with prior beliefs.
method Bayesian non-parametric algorithm based on Dirichlet Process priors.
result DPPS provides principled incorporation of prior beliefs and is optimal in Bayesian regret setup.
Proposes using DII to identify non-linear causal relationships in EU Allowances returns.
problem Identifying causal relationships in non-linear data of EU Allowances returns.
method Uses Differentiable Information Imbalance (DII) for non-parametric causal discovery compared to multivariate Granger causality.
result Significant overlap and differences in causal variables identified by linear and non-linear methods.
A tractable pseudo-metric for non-parametric distributions via SPD geometry.
problem Computing distances between non-parametric probability distributions is intractable.
method Two-stage framework: projection onto parametric family, embedding into SPD matrices.
result Closed-form pseudo-metric for two-sample hypothesis testing.
In this paper, we suggest a framework to make use of mutual information as a regularization criterion to train Auto-Encoders (AEs). In the proposed framework, AEs are regularized by minimization of the mutual information between input and encoding variables of AEs during the training phase. In order to estimate the ent…
New algorithm learns nonlinear phenomena from noisy local measurements without data exchange.
problem Learning nonlinear phenomena from noisy local measurements in a decentralized network.
method Non-parametric learning algorithm that spreads information only between neighboring nodes.
result Non-asymptotic estimation error bounds for the proposed method.
Study models Indian stock market using hyperbolic geometry for market stability and volatility analysis.
problem Identifying market stability and volatility in the Indian stock market.
method Modelled as a heterogeneous scale-free network, embedded in a 2D hyperbolic space, applied coalescent embedding, hyperbolic kmeans, and Bollinger Band analysis.
result Clusters in the embedded network better represent market communities than Euclidean clusters, allowing for early detection of market changes.
This article reviews the Author-Topic Model and presents a new non-parametric extension based on the Hierarchical Dirichlet Process. The extension is especially suitable when no prior information about the number of components necessary is available. A blocked Gibbs sampler is described and focus put on staying as clos…
Non-parametric time series forecasting without assuming a specific distribution.
problem Time series forecasting with numerical stability issues in classical models.
method Generates predictions by sampling from the empirical distribution of time series data.
result The proposed method produces reasonable forecasts without numerical stability issues.
A graph-based method for two-sample testing across connected nodes.
problem Identifying nodes where two probability distributions differ significantly.
method Collaborative non-parametric two-sample testing (CTST) framework.
result CTST outperforms independent node tests by leveraging graph structure.
This paper finds a unique partition of a sample space for estimating continuous distributions.
problem Estimating continuous probability distributions from finite samples.
method Equal-probability partition of the sample space using order statistics.
result The partition yields an entropy of log2(N+1) bits, providing a discrete entropy estimate.
Unified data representation learning improves non-parametric two-sample testing.
problem Improving non-parametric two-sample testing accuracy.
method Proposes RL-TST framework combining IRs and DRs for better test power.
result RL-TST outperforms existing methods by leveraging both IRs and DRs.
Datasets with hundreds of variables and many missing values are commonplace. In this setting, it is both statistically and computationally challenging to detect true predictive relationships between variables and also to suppress false positives. This paper proposes an approach that combines probabilistic programming, …
iCOS method estimates risk-neutral densities and option prices without model assumptions.
problem Estimating risk-neutral densities and option prices without model assumptions.
method Leverages Fourier-cosine technique using option-implied cosine series coefficients, without model assumptions.
result Effective in extracting information from option prices under various market conditions.
Formulates mechanics for probability distributions on statistical manifold.
problem Formulating mechanics for probability distributions on statistical manifold.
method Information-geometric formulation of Classical Mechanics on statistical manifold, using dually-flat connection and Hilbert bundle structure.
result Provides coherent formalism for Lagrangian and Hamiltonian mechanics on statistical bundle.
The method of covariate adjustment is often used for estimation of population average treatment effects in observational studies. Graphical rules for determining all valid covariate adjustment sets from an assumed causal graphical model are well known. Restricting attention to causal linear models, a recent article der…
Neural Networks trained with gradient descent are known to be susceptible to catastrophic forgetting caused by parameter shift during the training process. In the context of Neural Machine Translation (NMT) this results in poor performance on heterogeneous datasets and on sub-tasks like rare phrase translation. On the …
The Mutual Information (MI) is an often used measure of dependency between two random variables utilized in information theory, statistics and machine learning. Recently several MI estimators have been proposed that can achieve parametric MSE convergence rate. However, most of the previously proposed estimators have th…
Framework predicts Navier-Stokes solutions on 2D domains using graph neural networks.
problem Predicting stationary Navier-Stokes solutions in non-parametrized 2D geometries.
method Graph-based multi-fidelity learning framework combining reduced-order models, Transformers, and Mamba architectures.
result Mamba architecture reduces computational cost while maintaining performance.
Complex analytic sets' Lipschitz geometry at infinity characterized.
problem Characterize entire complex analytic sets based on their Lipschitz geometry at infinity.
method Proved a complex non-parametric version of Moser's Bernstein Theorem and characterized algebraicity.
result Entire complex analytic sets at infinity are affine linear subspaces if and only if they are bi-Lipschitz homeomorphic to algebraic sets.
The Fisher information matrix (FIM) is a foundational concept in statistical signal processing. The FIM depends on the probability distribution, assumed to belong to a smooth parametric family. Traditional approaches to estimating the FIM require estimating the probability distribution function (PDF), or its parameters…
The identification of relevant features, i.e., the driving variables that determine a process or the properties of a system, is an essential part of the analysis of data sets with a large number of variables. A mathematical rigorous approach to quantifying the relevance of these features is mutual information. Mutual i…
In order to study the geometry of interest rates market dynamics, Malliavin, Mancino and Recchioni [A non-parametric calibration of the HJM geometry: an application of Itô calculus to financial statistics, {\it Japanese Journal of Mathematics}, 2, pp.55--77, 2007] introduced a scheme, which is based on the Fourier Seri…
Automatically counts microglial cells in rat spinal cord images, providing precise counts and uncertainty estimates.
problem Counting microglial cells in small, heterogeneous datasets is time-consuming and requires extensive training.
method Pre-processing to filter images, designing a non-parametric, non-linear kernel counter, providing uncertainty estimation.
result The method can provide precise counts and uncertainty estimates in small datasets, even with expert opinions.
Meta learning with information theory and Gaussian processes.
problem Few-shot learning problems.
method Information bottleneck, mutual information, variational approximations, Gaussian processes.
result Competitive accuracy on few-shot classification problems.
KSD Thinning uses KSD to thin MCMC samples efficiently.
problem Efficiently representing posterior distributions in Bayesian inference.
method KSD Thinning: retains only samples exceeding a KSD threshold.
result Established convergence and complexity tradeoffs for KSD Thinning.
We present a dual-view mixture model to cluster users based on their features and latent behavioral functions. Every component of the mixture model represents a probability density over a feature view for observed user attributes and a behavior view for latent behavioral functions that are indirectly observed through u…
Data collection at a massive scale is becoming ubiquitous in a wide variety of settings, from vast offline databases to streaming real-time information. Learning algorithms deployed in such contexts must rely on single-pass inference, where the data history is never revisited. In streaming contexts, learning must also …
Ensembles of classification and regression trees remain popular machine learning methods because they define flexible non-parametric models that predict well and are computationally efficient both during training and testing. During induction of decision trees one aims to find predicates that are maximally informative …
Proposes method for eliciting non-parametric joint priors using normalizing flows.
problem Learning complex non-parametric joint priors for model parameters.
method Expert elicitation combined with normalizing flows for generative modeling.
result Framework supports elicitation of both parametric and non-parametric priors.
The Information bottleneck method is an unsupervised non-parametric data organization technique. Given a joint distribution P(A,B), this method constructs a new variable T that extracts partitions, or clusters, over the values of A that are informative about B. The information bottleneck has already been applied to doc…
This paper investigates the use of methods from partial differential equations and the Calculus of variations to study learning problems that are regularized using graph Laplacians. Graph Laplacians are a powerful, flexible method for capturing local and global geometry in many classes of learning problems, and the tec…
UMAP connects to Information Geometry principles.
problem None explicitly stated; focuses on connections.
method None explicitly stated; focuses on connections.
result UMAP has a natural geometric interpretation.
Active learning recovers choice model from noisy data.
problem Identifying non-parametric choice models from noisy data.
method Directed acyclic graph (DAG) representation and inclusion-exclusion approach.
result Algorithm more accurately recovers frequent preferences.
Symplectic and Poisson structures proved for information geometry's Frobenius manifold.
problem Connecting disconnected theories in information geometry.
method Proving symplectic and Poisson structures on the Frobenius manifold.
result Established a bridge between Vinberg, Souriau, and Koszul's theories.
Information geometry offers new tools for statistical analysis.
problem Statistical analysis of probability distributions.
method Geometric perspective on statistical manifolds.
result New applications in radar sensing, signal processing, etc.
Adversarially robust machine learning has received much recent attention. However, prior attacks and defenses for non-parametric classifiers have been developed in an ad-hoc or classifier-specific basis. In this work, we take a holistic look at adversarial examples for non-parametric classifiers, including nearest neig…
Information divergence functions play a critical role in statistics and information theory. In this paper we show that a non-parametric f-divergence measure can be used to provide improved bounds on the minimum binary classification probability of error for the case when the training and test data are drawn from the sa…
Parametric UMAP learns a mapping from data to embeddings.
problem Representing and learning from structured data.
method Parametric optimization over neural network weights for UMAP.
result Parametric UMAP performs comparably to non-parametric UMAP with faster online embeddings.
Develops information geometry for Lévy processes in finance.
problem Understanding the statistical properties of Lévy processes for financial modeling.
method Deriving α-divergences from Lévy triplets, identifying Fisher information matrix and α-connection. result Identifies statistical implications and differential-geometric structures of Lévy processes.
Survey of linking information geometry and optimal transport.
problem Connecting two geometric frameworks for probability measures.
method Exploration of interactions and links between information geometry and optimal transport.
result Outstanding questions for both disciplines.