arXiv research

New robustness test for kernel goodness-of-fit tests.

Sliced kernelized Stein discrepancy improves goodness-of-fit tests and model learning in high dimensions.

A new kernel Stein test assesses fit for variable-length sequential data.

A new framework improves kernel Stein discrepancy tests for validating distributions.

KSDAgg combines multiple KSD tests to improve goodness-of-fit testing without splitting data.

Improved KSD test for better detection of differences in distributions.

Paper develops a minimax optimal test for goodness-of-fit using kernel Stein discrepancy.

Fourier representation improves KSD for infinite-dimensional data.

A new sequential test for unnormalized densities.

Improved kernel Stein discrepancy for large-scale data.

A new test assesses how well observed networks fit a specified ERGM model.

We propose a nonparametric statistical test for goodness-of-fit: given a set of samples, the test determines how likely it is that these were generated from a target density function. The measure of goodness-of-fit is a divergence constructed via Stein's method using functions from a Reproducing Kernel Hilbert Space. O…

New test assesses probabilistic model calibration without expensive approximations.

Software package assesses spherical data distributions and clusters.

We derive a new discrepancy statistic for measuring differences between two probability distributions based on combining Stein's identity with the reproducing kernel Hilbert space theory. We apply our result to test how well a probabilistic model fits a set of observations, and derive a new class of powerful goodness-o…

Improved SSD for faster and more accurate goodness-of-fit tests and model learning.

We propose a novel adaptive test of goodness-of-fit, with computational cost linear in the number of samples. We learn the test features that best indicate the differences between observed samples and a reference model, by minimizing the false negative rate. These features are constructed via Stein's method, meaning th…

Paper proposes kernel-based tests for model misspecification.

Paper proposes kernelized Stein tests for time-to-event data with censoring.

New research sets the minimax lower bound for KSD estimation at sqrt(n).

The reproducing kernel Hilbert space (RKHS) embedding of distributions offers a general and flexible framework for testing problems in arbitrary domains and has attracted considerable amount of attention in recent years. To gain insights into their operating characteristics, we study here the statistical performance of…

Improved MMD test for non-Euclidean data with spectral regularization.

CSD improves goodness-of-fit testing for higher-order dependence.

We characterize the asymptotic performance of nonparametric goodness of fit testing. The exponential decay rate of the type-II error probability is used as the asymptotic performance metric, and a test is optimal if it achieves the maximum rate subject to a constant level constraint on the type-I error probability. We …

Unified framework for optimal kernel tests across MMD, HSIC, and KSD.

Unified score and distance-based GoF tests for model adequacy.

Two new tests assess how well conditional models fit data.

Much of machine learning relies on comparing distributions with discrepancy measures. Stein's method creates discrepancy measures between two distributions that require only the unnormalized density of one and samples from the other. Stein discrepancies can be combined with kernels to define kernelized Stein discrepanc…

Improving scalability and stability of Stein discrepancies for scalable goodness-of-fit testing

Study evaluates RKHS choices for assessing graph models using KSD tests.

New KSDs control moments in approximations, improving diagnostics and tests.

Nonparametric tests via kernel embedding of distributions have witnessed a great deal of practical successes in recent years. However, statistical properties of these tests are largely unknown beyond consistency against a fixed alternative. To fill in this void, we study here the asymptotic properties of goodness-of-fi…

Develops efficient inference for noise heterogeneity in machine learning models.

New Stein operator improves robustness in model inference.

HADES detects data singularities quickly and accurately.

We propose a kernel-based nonparametric test of relative goodness of fit, where the goal is to compare two models, both of which may have unobserved latent variables, such that the marginal distribution of the observed variables is intractable. The proposed test generalizes the recently proposed kernel Stein discrepanc…

The paper advances U-statistics in dependent settings, improving spectral estimation and goodness-of-fit tests.

Kernel tests assess equivalence between distributions without assuming specific moments.

Study optimizes KSD estimation from samples, revealing Hilbert-Schmidt vs trace scales.

Neyman-Pearson testing improves goodness of fit in detecting new physics.

In quantitative finance, we often fit a parametric semimartingale model to asset prices. To ensure our model is correct, we must then perform goodness-of-fit tests. In this paper, we give a new goodness-of-fit test for volatility-like processes, which is easily applied to a variety of semimartingale models. In each cas…

A method for efficient approximate inference on discrete distributions.

In this paper, we develop an efficient nonparametric Bayesian estimation of the kernel function of Hawkes processes. The non-parametric Bayesian approach is important because it provides flexible Hawkes kernels and quantifies their uncertainty. Our method is based on the cluster representation of Hawkes processes. Util…

A theoretical framework for non-negative matrix factorization based on generalized dual Kullback-Leibler divergence, which includes members of the exponential family of models, is proposed. A family of algorithms is developed using this framework and its convergence proven using the Expectation-Maximization algorithm. …

A new method for assessing Bayesian sampling quality, PSD, is proposed and shown to be more powerful and efficient.

Hawkes processes have seen a number of applications in finance, due to their ability to capture event clustering behaviour typically observed in financial systems. Given a calibrated Hawkes process, of concern is the statistical fit to empirical data, particularly for the accurate quantification of self- and mutual-exc…

New spectral tests assess network model fits efficiently.

Unified neural network model for astro-particle physics predictions with coverage, systematics, and goodness-of-fit.