# Testing probability distributions underlying aggregated data

arXiv: https://arxiv.org/abs/1402.3835 · HTML: https://mlsanity.com/paper/1402.3835/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Feb 2014.

## Built on by (most cited first, 15 of 15)

- [Learning-based Support Estimation in Sublinear Time](https://mlsanity.com/paper/2106.08396/) (2021)
- [Learning Hidden Markov Models Using Conditional Samples](https://mlsanity.com/paper/2302.14753/) (2023)
- [Lifting uniform learners via distributional decomposition](https://mlsanity.com/paper/2303.16208/) (2023)
- [Total Variation Distance Meets Probabilistic Inference](https://mlsanity.com/paper/2309.09134/) (2023)
- [Daisy Bloom Filters](https://mlsanity.com/paper/2205.14894/) (2022)
- [Optimal Algorithms for Augmented Testing of Discrete Distributions](https://mlsanity.com/paper/2412.00974/) (2024)
- [Approximating the total variation distance between spin systems](https://mlsanity.com/paper/2502.05437/) (2025)
- [Monotonicity Testing of High-Dimensional Distributions with Subcube Conditioning](https://mlsanity.com/paper/2502.16355/) (2025)
- [Total Variation Distance Estimation in Autoregressive Models](https://mlsanity.com/paper/2607.19510/) (2026)
- [Zero-Shot Attribution for Large Language Models: A Distribution Testing Approach](https://mlsanity.com/paper/2506.20197/) (2025)
- [Sampling and Identity-Testing Without Approximate Tensorization of Entropy](https://mlsanity.com/paper/2506.23456/) (2025)
- [Optimal Prediction-Augmented Algorithms for Testing Independence of Distributions](https://mlsanity.com/paper/2603.04635/) (2026)
- [Differentially Private Verification of Distribution Properties](https://mlsanity.com/paper/2604.10819/) (2026)
- [On Computing Total Variation Distance Between Mixtures of Product Distributions](https://mlsanity.com/paper/2605.03839/) (2026)
- [Fast Length-Squared Sampling for Positive-Semidefinite Matrices](https://mlsanity.com/paper/2608.12503/) (2026)

## Abstract (arXiv)

In this paper, we analyze and study a hybrid model for testing and learning probability distributions. Here, in addition to samples, the testing algorithm is provided with one of two different types of oracles to the unknown distribution D over [n]. More precisely, we define both the dual and cumulative dual access models, in which the algorithm A can both sample from D and respectively, for any i∈[n], - query the probability mass D(i) (query access); or - get the total mass of 1,dots,i, i.e. sumj=1i D(j) (cumulative access) These two models, by generalizing the previously studied sampling and query oracle models, allow us to bypass the strong lower bounds established for a number of problems in these settings, while capturing several interesting aspects of these problems -- and providing new insight on the limitations of the models. Finally, we show that while the testing algorithms can be in most cases strictly more efficient, some tasks remain hard even with this additional power.