Replicable Uniformity Testing

• URL: http://arxiv.org/abs/2410.10892v1
• Date: Sat, 12 Oct 2024 02:55:17 GMT
• Title: Replicable Uniformity Testing
• Authors: Sihan Liu, Christopher Ye,
• Abstract summary: This work revisits uniformity testing under the framework of algorithmic replicability. We obtain a replicable tester using only $tildeO(sqrtn varepsilon-2 rho-1)$ samples.
• Score: 1.5883812630616523
• License:
• Abstract: Uniformity testing is arguably one of the most fundamental distribution testing problems. Given sample access to an unknown distribution $\mathbf{p}$ on $[n]$, one must decide if $\mathbf{p}$ is uniform or $\varepsilon$-far from uniform (in total variation distance). A long line of work established that uniformity testing has sample complexity $\Theta(\sqrt{n}\varepsilon^{-2})$. However, when the input distribution is neither uniform nor far from uniform, known algorithms may have highly non-replicable behavior. Consequently, if these algorithms are applied in scientific studies, they may lead to contradictory results that erode public trust in science. In this work, we revisit uniformity testing under the framework of algorithmic replicability [STOC '22], requiring the algorithm to be replicable under arbitrary distributions. While replicability typically incurs a $\rho^{-2}$ factor overhead in sample complexity, we obtain a replicable uniformity tester using only $\tilde{O}(\sqrt{n} \varepsilon^{-2} \rho^{-1})$ samples. To our knowledge, this is the first replicable learning algorithm with (nearly) linear dependence on $\rho$. Lastly, we consider a class of ``symmetric" algorithms [FOCS '00] whose outputs are invariant under relabeling of the domain $[n]$, which includes all existing uniformity testers (including ours). For this natural class of algorithms, we prove a nearly matching sample complexity lower bound for replicable uniformity testing.

Related papers

• Simple and Nearly-Optimal Sampling for Rank-1 Tensor Completion via Gauss-Jordan [49.1574468325115]
  We revisit the sample and computational complexity of completing a rank-1 tensor in $otimes_i=1N mathbbRd$. We present a characterization of the problem which admits an algorithm amounting to Gauss-Jordan on a pair of random linear systems.
  arXiv  Detail & Related papers  (2024-08-10T04:26:19Z)
• A Unified Framework for Uniform Signal Recovery in Nonlinear Generative Compressed Sensing [68.80803866919123]
  Under nonlinear measurements, most prior results are non-uniform, i.e., they hold with high probability for a fixed $mathbfx*$ rather than for all $mathbfx*$ simultaneously. Our framework accommodates GCS with 1-bit/uniformly quantized observations and single index models as canonical examples. We also develop a concentration inequality that produces tighter bounds for product processes whose index sets have low metric entropy.
  arXiv  Detail & Related papers  (2023-09-25T17:54:19Z)
• Near-Optimal Bounds for Learning Gaussian Halfspaces with Random Classification Noise [50.64137465792738]
  We show that any efficient SQ algorithm for the problem requires sample complexity at least $Omega(d1/2/(maxp, epsilon)2)$. Our lower bound suggests that this quadratic dependence on $1/epsilon$ is inherent for efficient algorithms.
  arXiv  Detail & Related papers  (2023-07-13T18:59:28Z)
• Replicability in Reinforcement Learning [46.89386344741442]
  We focus on the fundamental setting of discounted MDPs with access to a generative model. Inspired by Impagliazzo et al. [2022], we say that an RL algorithm is replicable if, with high probability, it outputs the exact same policy after two executions.
  arXiv  Detail & Related papers  (2023-05-31T05:16:23Z)
• Replicable Clustering [57.19013971737493]
  We propose algorithms for the statistical $k$-medians, statistical $k$-means, and statistical $k$-centers problems by utilizing approximation routines for their counterparts in a black-box manner. We also provide experiments on synthetic distributions in 2D using the $k$-means++ implementation from sklearn as a black-box that validate our theoretical results.
  arXiv  Detail & Related papers  (2023-02-20T23:29:43Z)
• Complexity of High-Dimensional Identity Testing with Coordinate Conditional Sampling [5.3098033683382155]
  We study the identity testing problem for high-dimensional distributions. We consider a significantly weaker conditional sampling oracle, which we call the $mathsfCoordinate Oracle$. We prove that if an analytic property known as approximate tensorization of entropy holds for an $n$-dimensional visible distribution $mu$, then there is an efficient identity testing algorithm for any hidden distribution $pi$ using $tildeO(n/varepsilon)$ queries.
  arXiv  Detail & Related papers  (2022-07-19T06:49:24Z)
• Sharp Constants in Uniformity Testing via the Huber Statistic [16.384142529375435]
  Uniformity testing is one of the most well-studied problems in property testing. It is known that the optimal sample complexity to distinguish the uniform distribution on $m$ elements from any $epsilon$-far distribution with $1-delta probability is $n. We show that the collisions tester achieves a sharp maximal constant in the number of standard deviations of separation between uniform and non-uniform inputs.
  arXiv  Detail & Related papers  (2022-06-21T20:43:53Z)
• Private High-Dimensional Hypothesis Testing [4.133655523622441]
  We provide improved differentially private algorithms for identity testing of high-dimensional distributions. Specifically, we can test whether the distribution comes from $mathcalN(mu*, Sigma)$ for some fixed $mu*$ or from some $mathcalN(mu*, Sigma)$ with total variation distance at least $alpha$.
  arXiv  Detail & Related papers  (2022-03-03T06:25:48Z)
• Optimal Testing of Discrete Distributions with High Probability [49.19942805582874]
  We study the problem of testing discrete distributions with a focus on the high probability regime. We provide the first algorithms for closeness and independence testing that are sample-optimal, within constant factors.
  arXiv  Detail & Related papers  (2020-09-14T16:09:17Z)
• Model-Free Reinforcement Learning: from Clipped Pseudo-Regret to Sample Complexity [59.34067736545355]
  Given an MDP with $S$ states, $A$ actions, the discount factor $gamma in (0,1)$, and an approximation threshold $epsilon > 0$, we provide a model-free algorithm to learn an $epsilon$-optimal policy. For small enough $epsilon$, we show an improved algorithm with sample complexity.
  arXiv  Detail & Related papers  (2020-06-06T13:34:41Z)

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.