How to Verify Any (Reasonable) Distribution Property: Computationally Sound Argument Systems for Distributions

• URL: http://arxiv.org/abs/2409.06594v1
• Date: Tue, 10 Sep 2024 15:37:23 GMT
• Title: How to Verify Any (Reasonable) Distribution Property: Computationally Sound Argument Systems for Distributions
• Authors: Tal Herman, Guy Rothblum,
• Abstract summary: We study proof-systems that allow a probabilistic verifier to ascertain that the results of an analysis are approximately correct. We focus on distribution testing problems: verifying that an unknown distribution has a claimed property. Our main contribution is a interactive protocol between a verifier and an untrusted prover which can be used to verify any property.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: As statistical analyses become more central to science, industry and society, there is a growing need to ensure correctness of their results. Approximate correctness can be verified by replicating the entire analysis, but can we verify without replication? Building on a recent line of work, we study proof-systems that allow a probabilistic verifier to ascertain that the results of an analysis are approximately correct, while drawing fewer samples and using less computational resources than would be needed to replicate the analysis. We focus on distribution testing problems: verifying that an unknown distribution is close to having a claimed property. Our main contribution is a interactive protocol between a verifier and an untrusted prover, which can be used to verify any distribution property that can be decided in polynomial time given a full and explicit description of the distribution. If the distribution is at statistical distance $\varepsilon$ from having the property, then the verifier rejects with high probability. This soundness property holds against any polynomial-time strategy that a cheating prover might follow, assuming the existence of collision-resistant hash functions (a standard assumption in cryptography). For distributions over a domain of size $N$, the protocol consists of $4$ messages and the communication complexity and verifier runtime are roughly $\widetilde{O}\left(\sqrt{N} / \varepsilon^2 \right)$. The verifier's sample complexity is $\widetilde{O}\left(\sqrt{N} / \varepsilon^2 \right)$, and this is optimal up to $\polylog(N)$ factors (for any protocol, regardless of its communication complexity). Even for simple properties, approximately deciding whether an unknown distribution has the property can require quasi-linear sample complexity and running time. For any such property, our protocol provides a quadratic speedup over replicating the analysis.

Related papers

• Statistical-Computational Trade-offs for Density Estimation [60.81548752871115]
  We show that for a broad class of data structures their bounds cannot be significantly improved. This is a novel emphstatistical-computational trade-off for density estimation.
  arXiv  Detail & Related papers  (2024-10-30T15:03:33Z)
• Adaptive Data Analysis in a Balanced Adversarial Model [26.58630744414181]
  In adaptive data analysis, a mechanism gets $n$ i.i.d. samples from an unknown distribution $D$, and is required to provide accurate estimations. We consider more restricted adversaries, called emphbalanced, where each such adversary consists of two separated algorithms. We show that these stronger hardness assumptions are unavoidable in the sense that any computationally bounded emphbalanced adversary implies the existence of public-key cryptography.
  arXiv  Detail & Related papers  (2023-05-24T15:08:05Z)
• Robust Mean Estimation Without Moments for Symmetric Distributions [7.105512316884493]
  We show that for a large class of symmetric distributions, the same error as in the Gaussian setting can be achieved efficiently. We propose a sequence of efficient algorithms that approaches this optimal error. Our algorithms are based on a generalization of the well-known filtering technique.
  arXiv  Detail & Related papers  (2023-02-21T17:52:23Z)
• Simple Binary Hypothesis Testing under Local Differential Privacy and Communication Constraints [8.261182037130407]
  We study simple binary hypothesis testing under both local differential privacy (LDP) and communication constraints. We qualify our results as either minimax optimal or instance optimal.
  arXiv  Detail & Related papers  (2023-01-09T18:36:49Z)
• 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)
• Testing distributional assumptions of learning algorithms [5.204779946147061]
  We study the design of tester-learner pairs $(mathcalA,mathcalT)$. We show that if the distribution on examples in the data passes the tester $mathcalT$ then one can safely trust the output of the agnostic $mathcalA$ on the data.
  arXiv  Detail & Related papers  (2022-04-14T19:10:53Z)
• A Law of Robustness beyond Isoperimetry [84.33752026418045]
  We prove a Lipschitzness lower bound $Omega(sqrtn/p)$ of robustness of interpolating neural network parameters on arbitrary distributions. We then show the potential benefit of overparametrization for smooth data when $n=mathrmpoly(d)$. We disprove the potential existence of an $O(1)$-Lipschitz robust interpolating function when $n=exp(omega(d))$.
  arXiv  Detail & Related papers  (2022-02-23T16:10:23Z)
• Acceleration in Distributed Optimization Under Similarity [72.54787082152278]
  We study distributed (strongly convex) optimization problems over a network of agents, with no centralized nodes. An $varepsilon$-solution is achieved in $tildemathcalrhoObig(sqrtfracbeta/mu (1-)log1/varepsilonbig)$ number of communications steps. This rate matches (up to poly-log factors) for the first time lower complexity communication bounds of distributed gossip-algorithms applied to the class of problems of interest.
  arXiv  Detail & Related papers  (2021-10-24T04:03:00Z)
• The Sample Complexity of Robust Covariance Testing [56.98280399449707]
  We are given i.i.d. samples from a distribution of the form $Z = (1-epsilon) X + epsilon B$, where $X$ is a zero-mean and unknown covariance Gaussian $mathcalN(0, Sigma)$. In the absence of contamination, prior work gave a simple tester for this hypothesis testing task that uses $O(d)$ samples. We prove a sample complexity lower bound of $Omega(d2)$ for $epsilon$ an arbitrarily small constant and $gamma
  arXiv  Detail & Related papers  (2020-12-31T18:24:41Z)
• 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)
• Robustly Learning any Clusterable Mixture of Gaussians [55.41573600814391]
  We study the efficient learnability of high-dimensional Gaussian mixtures in the adversarial-robust setting. We provide an algorithm that learns the components of an $epsilon$-corrupted $k$-mixture within information theoretically near-optimal error proofs of $tildeO(epsilon)$. Our main technical contribution is a new robust identifiability proof clusters from a Gaussian mixture, which can be captured by the constant-degree Sum of Squares proof system.
  arXiv  Detail & Related papers  (2020-05-13T16:44:12Z)

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.