Robust hypothesis testing and distribution estimation in Hellinger distance

• URL: http://arxiv.org/abs/2011.01848v1
• Date: Tue, 3 Nov 2020 17:09:32 GMT
• Title: Robust hypothesis testing and distribution estimation in Hellinger distance
• Authors: Ananda Theertha Suresh
• Abstract summary: We propose a simple robust hypothesis test that has the same sample complexity as that of the optimal Neyman-Pearson test up to constants. We discuss the applicability of such a robust test for estimating distributions in Hellinger distance.
• Score: 18.950453666957692
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We propose a simple robust hypothesis test that has the same sample complexity as that of the optimal Neyman-Pearson test up to constants, but robust to distribution perturbations under Hellinger distance. We discuss the applicability of such a robust test for estimating distributions in Hellinger distance. We empirically demonstrate the power of the test on canonical distributions.

Related papers

• Theory on Score-Mismatched Diffusion Models and Zero-Shot Conditional Samplers [49.97755400231656]
  We present the first performance guarantee with explicit dimensional general score-mismatched diffusion samplers. We show that score mismatches result in an distributional bias between the target and sampling distributions, proportional to the accumulated mismatch between the target and training distributions. This result can be directly applied to zero-shot conditional samplers for any conditional model, irrespective of measurement noise.
  arXiv  Detail & Related papers  (2024-10-17T16:42:12Z)
• Uncertainty Quantification via Stable Distribution Propagation [60.065272548502]
  We propose a new approach for propagating stable probability distributions through neural networks. Our method is based on local linearization, which we show to be an optimal approximation in terms of total variation distance for the ReLU non-linearity.
  arXiv  Detail & Related papers  (2024-02-13T09:40:19Z)
• Using Perturbation to Improve Goodness-of-Fit Tests based on Kernelized Stein Discrepancy [3.78967502155084]
  Kernelized Stein discrepancy (KSD) is a score-based discrepancy widely used in goodness-of-fit tests. We show theoretically and empirically that the KSD test can suffer from low power when the target and the alternative distributions have the same well-separated modes but differ in mixing proportions.
  arXiv  Detail & Related papers  (2023-04-28T11:13:18Z)
• Doubly Robust Kernel Statistics for Testing Distributional Treatment Effects [18.791409397894835]
  We build upon a previously introduced framework, Counterfactual Mean Embeddings, for representing causal distributions within Reproducing Kernel Hilbert Spaces (RKHS) These improved estimators are inspired by doubly robust estimators of the causal mean, using a similar form within the kernel space. This leads to new permutation based tests for distributional causal effects, using the estimators we propose as tests statistics.
  arXiv  Detail & Related papers  (2022-12-09T15:32:19Z)
• Kernel Robust Hypothesis Testing [20.78285964841612]
  In this paper, uncertainty sets are constructed in a data-driven manner using kernel method. The goal is to design a test that performs well under the worst-case distributions over the uncertainty sets. For the Neyman-Pearson setting, the goal is to minimize the worst-case probability of miss detection subject to a constraint on the worst-case probability of false alarm.
  arXiv  Detail & Related papers  (2022-03-23T23:59:03Z)
• A Data-Driven Approach to Robust Hypothesis Testing Using Sinkhorn Uncertainty Sets [12.061662346636645]
  We seek the worst-case detector over distributional uncertainty sets centered around the empirical distribution from samples using Sinkhorn distance. Compared with the Wasserstein robust test, the corresponding least favorable distributions are supported beyond the training samples, which provides a more flexible detector.
  arXiv  Detail & Related papers  (2022-02-09T03:26:15Z)
• An $\ell^p$-based Kernel Conditional Independence Test [21.689461247198388]
  We propose a new computationally efficient test for conditional independence based on the $Lp$ distance between two kernel-based representatives of well suited distributions. We conduct a series of experiments showing that the performance of our new tests outperforms state-of-the-art methods both in term of statistical power and type-I error even in the high dimensional setting.
  arXiv  Detail & Related papers  (2021-10-28T03:18:27Z)
• Instance-Optimal Compressed Sensing via Posterior Sampling [101.43899352984774]
  We show for Gaussian measurements and emphany prior distribution on the signal, that the posterior sampling estimator achieves near-optimal recovery guarantees. We implement the posterior sampling estimator for deep generative priors using Langevin dynamics, and empirically find that it produces accurate estimates with more diversity than MAP.
  arXiv  Detail & Related papers  (2021-06-21T22:51:56Z)
• Balance-Subsampled Stable Prediction [55.13512328954456]
  We propose a novel balance-subsampled stable prediction (BSSP) algorithm based on the theory of fractional factorial design. A design-theoretic analysis shows that the proposed method can reduce the confounding effects among predictors induced by the distribution shift. Numerical experiments on both synthetic and real-world data sets demonstrate that our BSSP algorithm significantly outperforms the baseline methods for stable prediction across unknown test data.
  arXiv  Detail & Related papers  (2020-06-08T07:01:38Z)
• Minimax Optimal Estimation of KL Divergence for Continuous Distributions [56.29748742084386]
  Esting Kullback-Leibler divergence from identical and independently distributed samples is an important problem in various domains. One simple and effective estimator is based on the k nearest neighbor between these samples.
  arXiv  Detail & Related papers  (2020-02-26T16:37:37Z)
• Distributionally Robust Bayesian Quadrature Optimization [60.383252534861136]
  We study BQO under distributional uncertainty in which the underlying probability distribution is unknown except for a limited set of its i.i.d. samples. A standard BQO approach maximizes the Monte Carlo estimate of the true expected objective given the fixed sample set. We propose a novel posterior sampling based algorithm, namely distributionally robust BQO (DRBQO) for this purpose.
  arXiv  Detail & Related papers  (2020-01-19T12:00:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.