New framework improves experimental design using integral probability metrics.
problem Challenges in Bayesian Optimal Experimental Design (BOED) with KL divergence.
method Integrates integral probability metrics (IPMs) for stability and flexibility.
result IPM-based designs yield more robust and accurate credible sets.
Paper proposes a new FRL algorithm for continuous sensitive attributes using EIPM.
problem Existing FRL algorithms cannot handle continuous sensitive attributes.
method Introduces EIPM to assess fairness in representation space for continuous attributes and proposes FREM algorithm.
result FREM outperforms other methods in fairness evaluation for continuous sensitive attributes.
The paper bounds the expectation of empirical processes indexed by Hölder classes.
problem Estimating the expectation of the supremum of empirical processes for distributions on bounded sets.
method Providing upper bounds on the expectation of the supremum of empirical processes indexed by Hölder classes.
result Deriving non-asymptotic risk bounds for estimating distributions using empirical processes and IPM.
The paper explores statistical and topological properties of sliced probability divergences.
problem Understanding the topological, statistical, and computational consequences of slicing divergences.
method Deriving theoretical properties of sliced probability divergences, including metric axioms preservation and weak continuity.
result Sliced divergences share similar topological properties and have stable sample complexity.
While Gaussian probability densities are omnipresent in applied mathematics, Gaussian cumulative probabilities are hard to calculate in any but the univariate case. We study the utility of Expectation Propagation (EP) as an approximate integration method for this problem. For rectangular integration regions, the approx…
We find a simple expression for the probability density of ∫exp(Bs−s/2)ds in terms of its distribution function and the distribution function for the time integral of exp(Bs+s/2). The relation is obtained with a change of measure argument where expectations over events determined by the time integral…
This paper argues against using calibration metrics for assessing posterior probabilities and proposes expected proper scoring rules instead.
problem The assessment of posterior probabilities generated by machine learning classifiers using calibration metrics is flawed and should be replaced with expected proper scoring rules.
method The paper reviews proper scoring rules from a practical perspective, explains why expected PSRs are a principled measure of posterior quality, and introduces a new calibration metric called calibration loss.
result Calibration loss is superior to expected calibration error and expected score divergence calibration metrics for assessing posterior probabilities.
Choquet and minimax expectations are equivalent in European option pricing.
problem Pricing European options in incomplete markets.
method Comparing Choquet and minimax expectations in the context of European options.
result Choquet and minimax expectations are equal for European options.
We offer a simplified proof for Expected Shortfall's dual representation.
problem The dual representation of Expected Shortfall.
method Basic properties of quantile functions.
result New proof of Expected Shortfall's subadditivity.
This work introduces a new metric for comparing imprecise probability models.
problem Quantifying differences between imprecise probability models.
method Integral imprecise probability metric framework based on Choquet integral.
result IIPM enables comparison across different imprecise probability models and quantifies epistemic uncertainty.
Paper examines stability of Bayesian posterior measures using integral probability metrics.
problem Stability of Bayesian inference in large-scale inverse problems.
method New families of integral probability metrics for likelihood and prior perturbations.
result Constructs new stability results for Bayesian posterior measures.
We study the minimax optimal rates for estimating a range of Integral Probability Metrics (IPMs) between two unknown probability measures, based on n independent samples from them. Curiously, we show that estimating the IPM itself between probability measures, is not significantly easier than estimating the probabili…
Kernel DRO uses RKHS to optimize under distributional uncertainty.
problem Optimizing under distributional uncertainty with limited knowledge.
method Kernel DRO using RKHS ambiguity sets and duality theory.
result Unified approach to robust and stochastic optimization.
We provide a general theoretical analysis of expected out-of-sample utility, also referred to as decision-theoretic classification, for non-decomposable binary classification metrics such as F-measure and Jaccard coefficient. Our key result is that the expected out-of-sample utility for many performance metrics is prov…
A nonparametric two-sample test using a parametric integral probability metric
problem Detecting distributional differences between two independent samples
method Propose a new two-sample test statistic based on a newly introduced integral probability metric (IPM)
result Establish theoretical guarantees for the associated two-sample testing procedure
New bounds use IPMs to improve generalization in machine learning.
problem Improving generalization bounds in machine learning.
method PAC-Bayes bounds with Integral Probability Metrics (IPM).
result Natural interpolation between worst-case and favorable cases.
The paper evaluates functions of stable Lévy processes and their extrema efficiently.
problem Efficiently evaluating functions of stable Lévy processes and their extrema.
method Integral representations, conformal acceleration technique, simplified trapezoid rule.
result Efficient numerical procedures for cumulative probability distribution functions (cpdfs) are developed.
The paper provides statistical guarantees for generative models using dimension reduction.
problem Improving the quality of generative models without increasing dimensionality.
method Modeling generative devices as smooth transformations of a lower-dimensional space and using integral probability metrics.
result Established a risk bound showing the impact of dimension reduction on generative model error.
A new IPM uses ReLU networks to measure probability discrepancies.
problem Measuring the difference between two probability distributions in high dimensions.
method Proposes a new parametric IPM using ReLU neural networks to optimize and distinguish between distributions.
result The proposed IPM has good convergence rates and can be used as a surrogate for other IPMs.
Quantum probability metrics improve distribution comparison in high dimensions.
problem Challenges in comparing probability distributions, especially in high-dimensional and non-compact domains.
method Quantum probability metrics (QPMs) derived from quantum state spaces, overcoming limitations of MMD.
result QPMs offer enhanced sensitivity to subtle distributional differences in high dimensions and improve performance in generative modeling.
RS-NSGD improves SGD convergence for heavy-tailed noise.
problem Nonconvex optimization with heavy-tailed noise.
method Integrates direction normalization into subspace updates.
result Achieves better oracle complexity than full-dimensional normalized SGD.
Develops a new divergence framework that combines f-divergences and IPMs.
problem Comparing distributions that are not absolutely continuous.
method Introduces (f,Γ)-divergences as a two-stage mass-redistribution/mass-transport process. result Improves estimation, learning, and uncertainty quantification in GANs for heavy-tailed distributions.
The paper proposes a new method for covariate balancing using IPM to improve causal inference.
problem Covariate imbalance in causal inference weighting methods, especially when models are not correctly specified.
method The integral probability metric (IPM) is used to determine optimal weights for treated and control groups.
result The proposed method can be consistent without specifying either the propensity score or outcome regression model.
The paper introduces return parity for fairness in MDPs, addressing delayed and adverse effects.
problem Fairness in MDPs for dynamic domains with delayed and adverse effects.
method Proposes return parity, decomposes return disparity, and develops algorithms for state visitation distributional alignment.
result The proposed algorithms can successfully close the disparity gap while maintaining policy performance.
Develops a measure-theoretic framework for complex co-occurrence data.
problem Modeling and interpreting complex co-occurrences in high-dimensional data.
method Introduces measure-theoretic probability and conditional probability, investigates E-integrals.
result Establishes a rigorous measure-theoretic foundation for co-occurrence modeling.
Random covers of hyperbolic surfaces follow a specific probability measure.
problem Understanding the distribution of random covers of hyperbolic surfaces.
method Analyzing random covers subject to specific group isomorphism conditions.
result Asymptotic distribution of random covers according to a probability measure on moduli space of metric graphs.
Paper proposes new density estimators for high-dimensional data.
problem Prohibitive computational cost and slow convergence rate in high-dimensional density estimation.
method Adaptive hyperbolic cross density estimators in mixed smooth Sobolev spaces.
result Proposed estimators do not suffer curse of dimensionality under Integral Probability Metrics.
Unified view of KL-divergence and IPMs via DRE, with new DRM metrics.
problem Unified understanding of KL-divergence and IPMs.
method Unified representation via maximum likelihood density-ratio estimation (DRE).
result Unified form of IPMs and novel DRM metrics.
Integrates VAEs into EM for deep clustering and generation.
problem Clustering and generating new samples from complex distributions.
method Combines VAEs and EM, updating model parameters and refining cluster assignments.
result Superior clustering performance on MNIST and FashionMNIST.
Novel algorithm speeds up computation of Sobolev IPM for graph-based probability measures.
problem Efficient computation of Sobolev IPM for graph-based probability measures.
method Established relation between Sobolev norm and weighted Lp-norm, proposed novel regularization, leveraged graph structure. result Proposed regularized Sobolev IPM provides closed-form expression for fast computation.
The paper introduces metrics to rank potential outcomes for better decision-making.
problem Optimal action selection in uncertain situations using causal reasoning.
method Introducing two new metrics: probabilities of potential outcome ranking (PoR) and probability of achieving the best potential outcome (PoB). Establishing identification theorems and deriving bounds for these metrics, and presenting estimation methods.
result The estimators' finite-sample properties and their application to a real-world dataset are demonstrated.
This study analyzes how well GANs approximate distributions from small samples.
problem Understanding how well GANs approximate distributions from limited data.
method Analysis of GANs using integral probability metrics and Hölder classes.
result GANs can adaptively learn low-dimensional structures or Hölder densities.
A new method estimates multi-dimensional value distributions using Hilbert space embeddings.
problem Estimating value distributions in complex, multi-dimensional reinforcement learning settings.
method Hilbert space mappings and kernel mean embeddings to estimate the kernel mean embedding of multi-dimensional value distributions.
result Uniform convergence guarantees and robust off-policy evaluation demonstrated in simulations.
Identifies most probable flows for Kunita SDEs in fluid dynamics.
problem Modeling stochastic processes with Eulerian noise and deterministic drifts.
method Equipping the domain with a Riemannian metric from the noise, solving the resulting PDEs.
result Most probable flows differ from deterministic flows, especially under noise.
Study integrates implied Hurst exponent into IV models for better market efficiency.
problem Capturing market efficiency in IV models based on moneyness.
method Developed an IV model integrating implied Hurst exponent H, optimizing across multiple indexes.
result Model outperforms SABR and fSABR in accuracy, capturing IV-H dynamics.
New metrics avoid high-dimensional analysis challenges, proving convergence without 'curse of dimensionality'.
problem High-dimensional analysis challenges in empirical measure convergence.
method Proposed a new class of probability metrics free of the curse of dimensionality.
result Convergence of empirical measures is free of the curse of dimensionality.
We introduce a new notion of conditional nonlinear expectation under probability distortion. Such a distorted nonlinear expectation is not sub-additive in general, so it is beyond the scope of Peng's framework of nonlinear expectations. A more fundamental problem when extending the distorted expectation to a dynamic se…
New LFR algorithm ensures fair predictions with theoretical guarantees.
problem Ensuring fairness in AI algorithms for social decision-making.
method Proposes a new adversarial training scheme using IPM with a parametric family of discriminators.
result Theoretical guarantee of fairness in final prediction models.
New error bounds for GANs with nonlinear objective functions derived.
problem Statistical consistency of GANs with nonlinear objective functions.
method Derivation of statistical error bounds for (f,Γ)-GANs using Rademacher complexity. result Proves the statistical consistency of (f,Γ)-GANs. A new calibration metric bridges testability and actionability.
problem Combining testability and actionable insights for forecast probabilities.
method Cutoff Calibration Error (CCE) that assesses calibration over intervals of forecasted probabilities.
result Cutoff Calibration Error is both testable and actionable.
Deep neural networks can approximate any target probability distribution given certain conditions.
problem Approximating complex probability distributions with deep neural networks.
method Proving the existence of a deep neural network mapping that approximates a target distribution under various integral probability metrics.
result Upper bounds on the size of the neural network in terms of dimension and approximation error for different metrics.
New findings show fixed-kernel discriminators are weaker than feature-learning ones.
problem Comparing performance of fixed-kernel and feature-learning discriminators.
method Using function classes F2 and F1, constructing pairs of distributions, and linking IPMs with sliced Wasserstein distances. result Fixed-kernel IPM and SD cannot discriminate certain distributions that feature-learning IPM and SD can.
We propose a general information-theoretic approach called Seraph (SEmi-supervised metRic leArning Paradigm with Hyper-sparsity) for metric learning that does not rely upon the manifold assumption. Given the probability parameterized by a Mahalanobis distance, we maximize the entropy of that probability on labeled data…
We propose a general information-theoretic approach called Seraph (SEmi-supervised metRic leArning Paradigm with Hyper-sparsity) for metric learning that does not rely upon the manifold assumption. Given the probability parameterized by a Mahalanobis distance, we maximize the entropy of that probability on labeled data…
We study the systole of a random surface, where by a random surface we mean a surface constructed by randomly gluing together an even number of triangles. We study two types of metrics on these surfaces, the first one coming from using ideal hyperbolic triangles and the second one using triangles that carry a given Rie…
This research improves demand forecasting by predicting complete probability density functions using machine learning.
problem Forecasting complete probability density functions for better operational decision making.
method Supervised machine learning method 'Cyclic Boosting' for explainable predictions.
result Predicted probability density functions are fully explainable and avoid 'black-box' models.
New decision-theoretic calibration error metric improves prediction reliability.
problem Improving the reliability of predictions for decision-making.
method Proposed Calibration Decision Loss (CDL) and an efficient algorithm to achieve near-optimal CDL.
result Near-optimal CDL guarantees vanishing payoff loss from miscalibration.
Paper introduces a new project control method using Monte Carlo and statistical learning.
problem Project control under uncertainty.
method Integrates Earned Value Methodology with Monte Carlo simulation and statistical learning.
result Estimates probabilities of project success and duration.