Study shows how information loss and operation loss are related in feature representations.
problem Understanding the relationship between information loss and operation loss in feature representations.
method Analyzes the interplay between weak information loss and operation loss in continuous representations.
result Specific forms of vanishing information loss imply vanishing MPE loss in classification.
One of the most fundamental questions one can ask about a pair of random variables X and Y is the value of their mutual information. Unfortunately, this task is often stymied by the extremely large dimension of the variables. We might hope to replace each variable by a lower-dimensional representation that preserves th…
New method uses sufficient statistics to infer causal relationships from observational data.
problem Inferring causal relationships from observational data with hidden variables.
method Information Bottleneck method applied to find functional sufficient statistics.
result New causal rules not obtainable from standard methods, validated on simulated and real data.
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.
MSRL learns a representation maximizing mutual info with response variables.
problem Learning sufficient representations for complex, multi-dimensional data.
method Variational mutual information, deep neural networks, generalized Dudley's inequality.
result MSRL achieves consistent and accurate representation learning.
We introduce Minimal Achievable Sufficient Statistic (MASS) Learning, a training method for machine learning models that attempts to produce minimal sufficient statistics with respect to a class of functions (e.g. deep networks) being optimized over. In deriving MASS Learning, we also introduce Conserved Differential I…
LLMs' explanations are often insufficient and vary with input distribution.
problem Evaluating the sufficiency of LLM explanations without predefined biases.
method Generalizing sufficiency to arbitrary explanations, using LLM's input beliefs, and introducing SCSuff metric.
result Explanation sufficiency can vary with input distribution and is weakly correlated with model size, accuracy, or output entropy.
Two novel methods estimate multiple FDR directions for binary categorical responses.
problem Estimating multiple FDR directions for categorical responses.
method Information maximization and square loss mutual information.
result Statistical consistency of the proposed methods established.
Information geometry provides a geometric approach to families of statistical models. The key geometric structures are the Fisher quadratic form and the Amari-Chentsov tensor. In statistics, the notion of sufficient statistic expresses the criterion for passing from one model to another without loss of information. Thi…
New insights into encoder-decoder structures using information measures.
problem Understanding the role of encoder-decoder design in machine learning.
method Using information sufficiency and mutual information loss concepts.
result Characterizes the expressiveness loss in encoder-decoder designs.
Reduces IB problem to a simpler, lower-dimensional problem.
problem Information bottleneck problem in high-dimensional spaces.
method Identifies sufficient statistic that factors conditional distribution, reducing IB to a lower-dimensional problem.
result Preserves full IB curve and optimal representations, making IB tractable.
As financial instruments grow in complexity more and more information is neglected by risk optimization practices. This brings down a curtain of opacity on the origination of risk, that has been one of the main culprits in the 2007-2008 global financial crisis. We discuss how the loss of transparency may be quantified …
It is well-known that there are a number of relations between theoretical finance theory and information theory. Some of these relations are exact and some are approximate. In this paper we will explore some of these relations and determine under which conditions the relations are exact. It turns out that portfolio the…
We study the effect of the quality and quantity of side information on the recovery of a hidden community of size K=o(n) in a graph of size n. Side information for each node in the graph is modeled by a random vector with the following features: either the dimension of the vector is allowed to vary with n, while …
New statistics are introduced that maintain the Fisher metric structure closely, akin to sufficient statistics.
problem Maintaining the Fisher metric structure in statistical models.
method Characterizing statistics that maintain the Fisher metric structure bi-Lipschitz equivalently.
result Characterized statistics that preserve the Fisher metric structure closely.
Informed traders strategically reveal noisier signals, making prices less responsive to public information.
problem How informed traders strategically reveal signals impacts market prices and utility.
method Modeling a market with an informed trader, an uninformed trader, and liquidity providers, proving equilibrium existence.
result In equilibrium, the insider strategically reveals a noisier signal, making prices less responsive to public information.
Study quantifies information borrowing in hierarchical Bayesian models.
problem Impact of shared hyperparameters on posterior inference.
method Non-asymptotic framework, nested hierarchical prior distribution, integrated risk measure.
result Deeper hierarchical models outperform nested ones under certain conditions.
Study on how optimal representations emerge during deep learning training, focusing on the role of implicit regularization.
problem Understanding how optimal representations for tasks are learned during training.
method Investigates the role of implicit regularization in learning minimal sufficient representations, analyzing changes in representation content during training.
result Semantically meaningful but ultimately irrelevant information is encoded in early transient dynamics of training, which is later discarded.
The study explores generalized divergences and exponential families with a focus on sufficient conditions and laws of large numbers.
problem Generalization of Kullback-Leibler divergence and exponential families.
method Investigation of (h,τ)-divergence and (h,τ)-exponential families, definition of (h,τ)-dependence, proof of law of large numbers. result Sufficient condition for (h,τ)-divergence to induce Hessian structure on (h,τ)-exponential family, proof of law of large numbers. InfoPrompt improves soft prompt tuning by maximizing mutual information, leading to better performance.
problem High sensitivity of prompt tuning to initial conditions and insufficient task-relevant information.
method Develops an information-theoretic framework to maximize mutual information between prompts and model parameters, using novel loss functions.
result InfoPrompt accelerates convergence and outperforms traditional methods.
The purpose of sufficient dimension reduction (SDR) is to find the low-dimensional subspace of input features that is sufficient for predicting output values. In this paper, we propose a novel distribution-free SDR method called sufficient component analysis (SCA), which is computationally more efficient than existing …
In this paper, we consider a dynamic asset pricing model in an approximate fractional economy to address empirical regularities related to both investor protection and past information. Our newly developed model features not only in terms with a controlling shareholder who diverts a fraction of the output, but also goo…
PSMM method optimizes matrix sufficient dimension reduction.
problem Feature matrices with row- and column-wise interpretations require efficient dimension reduction.
method PSMM method converts matrix problem into classification problems using rank-1 normal matrix.
result PSMM outperforms existing methods and provides strong interpretability.
Market efficiency at least requires the absence of weak arbitrage opportunities, but this is not sufficient to establish a situation where the market is sensitive, i.e., where it "fully reflects" or "rapidly adjusts to" some information flow including the evolution of asset prices. By contrast, No Weak Arbitrage togeth…
The study extends stochastic block models to geometric settings, focusing on community detection and information flow.
problem Generalizing community detection and information flow models to geometric settings.
method Considered a geometric random graph over a homogeneous metric space, defined a geometric counterpart of flow of information on trees.
result Sufficient conditions for recovering locations and for percolation of information in geometric settings.
Does adding a theorem to a paper affect its chance of acceptance? Does labeling a post with the author's gender affect the post popularity? This paper develops a method to estimate such causal effects from observational text data, adjusting for confounding features of the text such as the subject or writing quality. We…
Study on sparse recovery with mixed-quality data, establishing sample-size conditions.
problem Sparse recovery with heterogeneous noise from high- and low-quality sources.
method Establishes linear trade-off for sufficient conditions, analyzes LASSO algorithm.
result Linear trade-off for sufficient conditions, robustness of LASSO to data heterogeneity.
FSRL balances fairness and sufficiency in learning representations.
problem Ensuring unbiased predictions and decisions in machine learning.
method A convex combination of sufficiency and fairness objectives using distance covariance.
result FSRL achieves a superior trade-off between fairness and accuracy.
Neural networks help create summary statistics for complex models.
problem Creating summary statistics for models with intractable likelihood functions.
method Infomax learning with neural networks to maximize mutual information.
result Improves performance of approximate Bayesian computation and neural likelihood methods.
Study online multiclass classification under bandit feedback, extending previous results.
problem Online multiclass classification with bandit feedback, focusing on label space unboundedness.
method Extend Daniely and Helbertal's results, show necessity and sufficiency of Bandit Littlestone dimension for learnability.
result Sequential uniform convergence is necessary but not sufficient for bandit online learnability.
Study shows how leveraging hierarchical similarity graphs improves matrix completion in recommender systems.
problem Improving matrix completion in recommender systems using hierarchical similarity graphs.
method Characterizes the optimal sample complexity using hierarchical stochastic block models and low-rank rating matrices.
result Exploiting hierarchical structure of social graphs significantly reduces the number of observed entries needed for accurate matrix completion.
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.
Generalizing empirical findings to new environments, settings, or populations is essential in most scientific explorations. This article treats a particular problem of generalizability, called "transportability", defined as a license to transfer information learned in experimental studies to a different population, on …
The problem of finding a reduced dimensionality representation of categorical variables while preserving their most relevant characteristics is fundamental for the analysis of complex data. Specifically, given a co-occurrence matrix of two variables, one often seeks a compact representation of one variable which preser…
This paper provides sufficient conditions for the time of bankruptcy (of a company or a state) for being a totally inaccessible stopping time and provides the explicit computation of its compensator in a framework where the flow of market information on the default is modelled explicitly with a Brownian bridge between …
We define the information threshold in Bayesian decision-making.
problem Understanding the optimal amount of information for reliable classification.
method Defining the information threshold as the point of maximum curvature in the prior vs. posterior curve.
result At the information threshold, additional evidence does not significantly improve posterior probability.
New neural network method simplifies high-dimensional data.
problem Scalability issues in nonlinear sufficient dimension reduction.
method Stochastic neural network with adaptive gradient algorithm.
result Proposed method outperforms existing methods on large-scale data.
The introduction of data analytics into medicine has changed the nature of patient treatment. In this, patients are asked to disclose personal information such as genetic markers, lifestyle habits, and clinical history. This data is then used by statistical models to predict personalized treatments. However, due to pri…
Study graph-based algorithms for multi-manifold clustering with sufficient conditions.
problem Clustering data from a union of manifolds with different dimensions and intersections.
method Investigate sufficient conditions for similarity graphs to capture geometric information.
result High probability error bounds for spectral approximation of tensorized Laplacian.
We consider forecasting a single time series when there is a large number of predictors and a possible nonlinear effect. The dimensionality was first reduced via a high-dimensional (approximate) factor model implemented by the principal component analysis. Using the extracted factors, we develop a novel forecasting met…
In this paper, we propose an information-theoretic exploration strategy for stochastic, discrete multi-armed bandits that achieves optimal regret. Our strategy is based on the value of information criterion. This criterion measures the trade-off between policy information and obtainable rewards. High amounts of policy …
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.
The principal support vector machines method (Li et al., 2011) is a powerful tool for sufficient dimension reduction that replaces original predictors with their low-dimensional linear combinations without loss of information. However, the computational burden of the principal support vector machines method constrains …
Paper defines saddle points in asymmetric Dynkin games using martingale theory.
problem Tackles saddle point conditions in asymmetric Dynkin games with partial information.
method Uses martingale theory to identify super and submartingales related to equilibrium payoffs.
result Characterizes saddle point strategies in terms of equilibrium payoffs' dynamics and Doob-Meyer decompositions.
We describe Information Forests, an approach to classification that generalizes Random Forests by replacing the splitting criterion of non-leaf nodes from a discriminative one -- based on the entropy of the label distribution -- to a generative one -- based on maximizing the information divergence between the class-con…
GenSDR tackles SDR by leveraging generative models to fully recover lower-dimensional structures.
problem Challenges in identifying low-dimensional sufficient structures in nonlinear SDR.
method Proposes GenSDR, a method that uses modern generative models to fully recover information in the central σ-field.
result Establishes consistency of GenSDR estimator for sample-level data and extends its applicability to non-Euclidean responses.
CCM improves context for Meta-RL by contrastive learning.
problem Improving context for Meta-RL to enable task generalization.
method CCM framework using contrastive learning for context encoding and information-gain-based trajectory collection.
result CCM outperforms state-of-the-art algorithms in benchmarks and sparse-reward environments.
FlowSDR learns a low-dimensional projection preserving the response's conditional distribution.
problem Learning a low-dimensional projection that captures the response's conditional distribution.
method FlowSDR uses conditional log-likelihood maximization with monotone rational-quadratic spline flows to learn the projection and conditional density.
result FlowSDR outperforms existing SDR methods in various simulation settings and a face-age prediction task.