Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 2610.25821

Optimal Priors for Betting Tests with Bounded Payoffs: An Exact Efficiency Characterization

Francesco Orabona
View original source ↗Read source document ↗Export metadata ↓

Abstract

Testing by betting is a powerful framework that recasts hypothesis testing as a betting game. A popular approach uses an $F$-weighted portfolio with a predefined prior $F$. For suitable priors, this approach has recently been shown to achieve the optimal expected rejection time as the error probability goes to zero at a fixed alternative. Yet, the prior $F$ changes how the portfolio test behaves near the null. This motivates the question: Which prior should we use in testing-by-betting algorithms? We study bounded scalar payoffs and introduce an efficiency measure that allows the error probability and alternative to vary jointly. Under mild assumptions, we prove that efficiency equals a logarithmic decay index of the prior near zero. This gives a necessary and sufficient condition for optimality: Beta priors have infinite efficiency, whereas suitable Robbins-type priors attain efficiency 1. As an application, we consider testing a specified mean of a bounded random variable and describe an implementation of the portfolio algorithm with almost-linear computational complexity.

Explore related subjects

math.STcs.ITmath.ITstat.MEstat.TH

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Francesco Orabona. 2026-10-19. Optimal Priors for Betting Tests with Bounded Payoffs: An Exact Efficiency Characterization. https://arxiv.org/abs/2610.25821

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Axioms for validity: e-values, p-values and data-dependent levels

The emerging literature on hypothesis testing with data-dependent significance levels relies on a particular extension of the Type-I error. Existing arguments for this extension are heuristic. We show it is uniquely characterized by three axioms: law-invariance, agreement with classical testing on constant levels, and the preservation of (in)validity under independent selection of the level. We find that three analogous axioms characterize the e-value as a multi-decision generalization of a test in a decision-theoretic framework. We recover the p-value by dropping the invalidity half of the independent selection axiom, showing that e-values correspond to those p-values for which a data-independent choice between two invalid p-values cannot produce a valid p-value. Our main technical contribution is to show how e-values emerge in every decision problem with a notion of validity that satisfies law invariance, the independent selection axiom, and an axiom stating that a procedure that selects an invalid procedure with arbitrarily high probability must itself be invalid. In an application to post-hoc decision-making, we justify expectation-based error rates in multiple testing and recover the 'e-closure principle' as a special case.

math.ST↗
arXiv2026

Optimal Community Recovery by Spectrally Initialized Variational EM in General Stochastic Block Models

We prove a Chernoff-exponent guarantee for the output of spectrally initialized batch variational EM after a prescribed iteration budget, without assuming global maximization of its variational objective. The iteration repeatedly estimates the entire block probability matrix and community proportions from the same sparse graph. We consider a fixed number of communities with proportions bounded away from zero and fixed, positive, distinct connectivity profiles; neither assortativity nor full rank is required. The algorithm uses simultaneous softmax updates without sample splitting or posterior thresholding. Its analysis must control the feedback between estimated parameters, soft labels and reused edges at an exponentially small risk scale. We establish a uniform one-step bound over data-dependent soft assignments whose random remainder has exponentially small expectation. Combined with an exponentially reliable regularized spectral initializer, this yields an unconditional expected misclassification rate bounded by $\exp\{-(1-o(1))J_n\}$ throughout the sparse, diverging-degree regime, where $J_n$ is the minimum nodewise Chernoff information. Matching lower bounds establish first-order logarithmic minimax optimality on local parameter spaces allowing unknown connectivity and varying community counts. The algorithm also attains the sharp first-order exact-recovery threshold. Numerical experiments illustrate refinement gains and sensitivity to initialization and imbalance.

math.ST↗
arXiv2026

Weak Limits of Parameter Estimation in Strongly Identifiable Mixture Models

We study the asymptotic behavior of global maximum likelihood estimation in finite mixtures with an unknown number of components bounded by \(k\). Although convergence rates are well understood under strong identifiability, they do not determine the limiting distribution of mixing-measure loss. Under second-order strong identifiability, we establish two geometric results that connect density asymptotics to uncertainty about the mixing measure. First, we characterize the exact attainable density tangent set, accounting for the component budget shared by nonlocal vanishing components and local splitting directions. Second, we derive a sequential first-order expansion of squared Wasserstein loss, showing that its leading transportation cost is uniquely determined by the relative-density direction. Together with a Gaussian likelihood argmax theorem, these results yield joint weak convergence of the relative-density maximum likelihood estimator and \(\sqrt n W_2^2(\widehat G_n,G_*)\). The density limit maximizes a Gaussian likelihood process over the attainable tangent set, and the induced limit of \(n^{1/4}W_2(\widehat G_n,G_*)\) is generally non-Gaussian. We establish consistency of an \(m\)-out-of-\(n\) parametric bootstrap when \(m\to\infty\) and \(m/n\to0\). Numerical studies assess the approximation and distinguish bootstrap and optimization errors; a flow-cytometry application illustrates uncertainty summaries invariant to component labeling under a working mixture model.

math.ST↗