# On nonnegative unbiased estimators

arXiv: https://arxiv.org/abs/1309.6473 · HTML: https://mlsanity.com/paper/1309.6473/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Sep 2013.

## Built on by (most cited first, 4 of 4)

- [On Feynman--Kac training of partial Bayesian neural networks](https://mlsanity.com/paper/2310.19608/) (2023)
- [Distributed data analytics](https://mlsanity.com/paper/2203.14088/) (2022)
- [Markov chain Monte Carlo without evaluating the target: an auxiliary variable approach](https://mlsanity.com/paper/2406.05242/) (2024)
- [Tempered Sequential Monte Carlo for Trajectory and Policy Optimization with Differentiable Dynamics](https://mlsanity.com/paper/2604.21456/) (2026)

## Abstract (arXiv)

We study the existence of algorithms generating almost surely nonnegative unbiased estimators. We show that given a nonconstant real-valued function f and a sequence of unbiased estimators of λ∈ℝ, there is no algorithm yielding almost surely nonnegative unbiased estimators of f(λ)∈ℝ^+. The study is motivated by pseudo-marginal Monte Carlo algorithms that rely on such nonnegative unbiased estimators. These methods allow "exact inference" in intractable models, in the sense that integrals with respect to a target distribution can be estimated without any systematic error, even though the associated probability density function cannot be evaluated pointwise. We discuss the consequences of our results on the applicability of pseudo-marginal algorithms and thus on the possibility of exact inference in intractable models. We illustrate our study with particular choices of functions f corresponding to known challenges in statistics, such as exact simulation of diffusions, inference in large datasets and doubly intractable distributions.