Exact Paired-Permutation Testing for Structured Test Statistics

• URL: http://arxiv.org/abs/2205.01416v2
• Date: Wed, 4 May 2022 09:28:59 GMT
• Title: Exact Paired-Permutation Testing for Structured Test Statistics
• Authors: Ran Zmigrod, Tim Vieira, Ryan Cotterell
• Abstract summary: We provide an efficient exact algorithm for the paired-permutation test for a family of structured test statistics. Our exact algorithm was $10$x faster than the Monte Carlo approximation with $20000$ samples on a common dataset.
• Score: 67.71280539312536
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Significance testing -- especially the paired-permutation test -- has played a vital role in developing NLP systems to provide confidence that the difference in performance between two systems (i.e., the test statistic) is not due to luck. However, practitioners rely on Monte Carlo approximation to perform this test due to a lack of a suitable exact algorithm. In this paper, we provide an efficient exact algorithm for the paired-permutation test for a family of structured test statistics. Our algorithm runs in $\mathcal{O}(GN (\log GN )(\log N ))$ time where $N$ is the dataset size and $G$ is the range of the test statistic. We found that our exact algorithm was $10$x faster than the Monte Carlo approximation with $20000$ samples on a common dataset.

Related papers

• The Limits of Assumption-free Tests for Algorithm Performance [6.7171902258864655]
  How well does an algorithm perform at a given modeling task, and which algorithm performs best? We make a distinction between two questions: how good is an algorithm $A$ at the problem of learning from a training set of size $n$, versus, how good is a particular fitted model produced by running $A$ on a particular training data set of size $n$?
  arXiv  Detail & Related papers  (2024-02-12T03:19:30Z)
• Collaborative non-parametric two-sample testing [55.98760097296213]
  The goal is to identify nodes where the null hypothesis $p_v = q_v$ should be rejected. We propose the non-parametric collaborative two-sample testing (CTST) framework that efficiently leverages the graph structure. Our methodology integrates elements from f-divergence estimation, Kernel Methods, and Multitask Learning.
  arXiv  Detail & Related papers  (2024-02-08T14:43:56Z)
• Testable Learning with Distribution Shift [9.036777309376697]
  We define a new model called testable learning with distribution shift. We obtain provably efficient algorithms for certifying the performance of a classifier on a test distribution. We give several positive results for learning concept classes such as halfspaces, intersections of halfspaces, and decision trees.
  arXiv  Detail & Related papers  (2023-11-25T23:57:45Z)
• Information-Computation Tradeoffs for Learning Margin Halfspaces with Random Classification Noise [50.64137465792738]
  We study the problem of PAC $gamma$-margin halfspaces with Random Classification Noise. We establish an information-computation tradeoff suggesting an inherent gap between the sample complexity of the problem and the sample complexity of computationally efficient algorithms.
  arXiv  Detail & Related papers  (2023-06-28T16:33:39Z)
• 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)
• Adjusted chi-square test for degree-corrected block models [13.122543280692641]
  We propose a goodness-of-fit test for degree-corrected block models (DCSBM) We show that a simple adjustment allows the statistic to converge in distribution, under null, as long as the harmonic mean of $d_i$ grows to infinity. Our distributional results are nonasymptotic, with explicit constants, providing finite-sample bounds on the Kolmogorov-Smirnov distance to the target distribution.
  arXiv  Detail & Related papers  (2020-12-30T05:20:59Z)
• List-Decodable Mean Estimation in Nearly-PCA Time [50.79691056481693]
  We study the fundamental task of list-decodable mean estimation in high dimensions. Our algorithm runs in time $widetildeO(ndk)$ for all $k = O(sqrtd) cup Omega(d)$, where $n$ is the size of the dataset. A variant of our algorithm has runtime $widetildeO(ndk)$ for all $k$, at the expense of an $O(sqrtlog k)$ factor in the recovery guarantee
  arXiv  Detail & Related papers  (2020-11-19T17:21:37Z)
• 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)
• Downsampling for Testing and Learning in Product Distributions [24.48103093661132]
  We study distribution-free property testing and learning problems where the unknown probability distribution is a product distribution over $mathbbRd$ For many important classes of functions, such as intersections of halfspaces, threshold functions, convex sets, and $k$-alternating functions, known algorithms either have complexity that depends on the support size of the distribution. We introduce a general method, which we call downlog, that resolves these issues.
  arXiv  Detail & Related papers  (2020-07-15T02:46:44Z)

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.