---
title: Asymptotic Anytime-Valid Confidence Sequences
url: https://www.emergentmind.com/topics/asymptotic-anytime-valid-confidence-sequences
type: topic
---

# Asymptotic Anytime-Valid Confidence Sequences

An asymptotic anytime-valid confidence sequence (AA-CS) is a sequence of intervals or sets for a target parameter, constructed so that, with high probability (at least \(1-\alpha\)), the parameter is contained in all intervals, uniformly over time, after a suitable burn-in. This property is guaranteed even under continuous monitoring and arbitrary stopping rules. The "asymptotic" qualifier indicates that the time-uniform guarantee is achieved in the large-sample limit, under weak moment or regularity conditions, rather than for all finite samples as in classical nonasymptotic CSs. AA-CSs blend the strengths of CLT-based inference (minimal assumptions, sharp asymptotic coverage) with the time-uniform error control required for safe sequential analysis.

## 1. Foundations and Definitions

The definition of an asymptotic anytime-valid confidence sequence is formalized through two essential features: (i) time-uniform coverage and (ii) asymptotic sharpness. For a parameter \(\theta\) of interest, an AA-CS is a sequence of intervals/processes \(\{C_t\}_{t \in \mathbb{N}}\) such that for all \(\alpha \in (0,1)\),
\[
\limsup_{m\to\infty} \mathbb{P}\Big( \exists t \geq m : \theta \notin C_t \Big) \leq \alpha.
\]
This means that, for sufficiently large sample size (after a burn-in \(m\)), the probability that \(\theta\) is ever excluded drops to at most \(\alpha\), and the size of \(C_t\) shrinks with \(t\) at CLT-optimal or nearly-optimal rates. For example, for the mean of i.i.d. variables with finite variance, AA-CS widths are typically \(O(\sqrt{\log t / t})\) or even \(O(\sqrt{\log\log t / t})\) [2103.06476, 2502.10380, 2311.03343].

A key distinction from classical fixed-time intervals or nonasymptotic CSs is that AA-CSs remain correct under arbitrary stopping (including data-dependent rules), with only a mild price in width for time-uniformity, and reduced regularity restrictions compared to nonasymptotic CSs (which require e.g. sub-Gaussian or bounded increments).

## 2. Core Methodology: Martingale Construction and Asymptotic Approximation

The construction of AA-CSs is generally based on explicit strong invariance (coupling) principles, martingale super/submartingale constructions, and mixture martingale (Bayesian mixture) boundaries. The principal recipe, formalized in [2103.06476, 2502.10380], consists of the following steps:
- **Step 1:** Obtain a strong invariance principle (e.g., Strassen’s theorem) to couple the empirical process (e.g., partial sums of centered data) to a Gaussian process, uniformly over all times \(t\), up to a \(o(\sqrt{t})\) error.
- **Step 2:** Design an explicit, time-uniform Gaussian boundary (e.g., Robbins–Siegmund mixture or law-of-iterated-logarithm (LIL) boundary) that serves as an envelope for the coupled process.
- **Step 3:** Use plug-in variance or covariance estimators, supported by their strong consistency, to transfer the Gaussian boundary to the empirical process.
- **Step 4:** Invert the acceptance region of an associated e-process or test-martingale to obtain the AA-CS.

The mathematical core of these constructions exploits the predictability of the empirical process, the pathwise properties of strong invariance, and Ville’s maximal inequality or its asymptotic variant for supermartingales [2210.01948, 2502.10380].

## 3. Explicit Forms and Shrinkage Rates

The canonical instantiation for the population mean \(\mu\) of an i.i.d. sequence with variance \(\sigma^2\) is
\[
C_t^{\text{Asymp}} = \Big[\, \widehat{\mu}_t \pm \widehat{\sigma}_t\, \sqrt{\frac{2(t\rho^2+1)}{t^2\rho^2} \ln\left(\frac{\sqrt{t\rho^2+1}}{\alpha}\right)} \,\Big],
\]
where \(\widehat{\mu}_t\) and \(\widehat{\sigma}_t\) are the sample mean/standard deviation, and \(\rho > 0\) is a tunable parameter to minimize boundary width at a desired horizon [2103.06476, 2302.10108, 2311.03343]. This boundary is valid uniformly over all times, is minimax rate-optimal in width, and shrinks at \(O(\sqrt{\log t/t})\), closely matching classical CLT intervals.

Sharper variants with adaptivity or improved sharpness can be obtained via choices of \(\gamma_1,\gamma_2\) in a flexible boundary family [2502.10380]. In high-dimensional or multi-parameter settings (such as the mean vector of a stochastic approximation), explicit multivariate boundaries based on the LIL or Gaussian-mixture argument achieve asymptotic time-uniform validity [2410.15057].

In structured settings, such as parametric models or linear regression, AA-CSs can be derived via inversion of sequential likelihood ratios, test martingales, or mixture e-processes, yielding intervals that asymptotically coincide with fixed-sample Wald intervals in both position and width [2310.03722, 2210.08589, 2210.01948].

## 4. Robustness, Uniformity, and Model Requirements

A central strength of the AA-CS paradigm is robustness to distributional deviations: it applies under minimal assumptions (finite second moments, martingale dependence), and can be proved both pointwise (for a given law) and uniformly over classes of laws \(\mathcal{P}\). The notion of distribution-uniform AA-CS, formalized by [2311.03343], ensures that the asymptotic time-uniform error control holds simultaneously over all \(P \in \mathcal{P}\), under the existence of sufficient moments. For instance, the 'Robbins–Siegmund' boundary with an empirical variance plug-in achieves such \(\mathcal{P}\)-uniformity with only a mild logarithmic penalty in boundary width.

For regression and double/debiased machine learning (DML) settings [2408.09598, 2210.08589], the resulting AA-CSs require only rates of cross-fitted nuisance parameter estimation faster than \(o(\sqrt{\log\log n / n})\), and they remain valid under arbitrary stopping/tuning, a crucial property for modern adaptive or online causal inference pipelines.

AA-CSs have also been developed and analyzed for nonparametric or heavy-tailed settings, including explicit lower confidence sequences for right heavy-tailed data [2210.11133], and multinomial or multivariate cases [2011.03567].

## 5. Practical Stopping Rules and Applications

The time-uniform property of AA-CSs enables the design of stopping rules that are both adaptive and statistically principled. The usual strategy is to halt when the width of the CS drops below a user-specified threshold, or when the null is excluded [2512.13123, 2302.10108].

For example, in stochastic approximation and SGD, the stopping time
\[
\tau_\varepsilon = \inf \{ t \geq 1 : U_t(\alpha) \leq \varepsilon \}
\]
for an upper AA-CS \(U_t(\alpha)\) for average suboptimality, is almost surely finite, and at \(\tau_\varepsilon\), the guarantee \(\mathbb{P}(f(\overline{x}_{\tau_\varepsilon}) - f^* \leq \varepsilon) \geq 1 - \alpha\) holds [2512.13123].

AA-CSs now underpin several deployed and large-scale experimental platforms, including A/B testing infrastructure for Adobe Experience Platform [2302.10108], and sequential analyses in contemporary industrial settings; they are vital for adaptive experimentation, best-arm identification, and anytime-robust estimation in sequential machine learning and statistics [2601.00084, 2311.05794].

A table listing representative AA-CS constructions is included below for reference.

| Paper                | Problem Type                  | AA-CS Boundary (width)                     | Main Assumptions              |
|----------------------|------------------------------|--------------------------------------------|-------------------------------|
| [2103.06476]         | Mean, Martingale/ATE         | \(O(\sqrt{\log t/t})\)                     | finite variance/invariance     |
| [2502.10380]         | Mean, flexible boundary      | \(O(\sqrt{\log t/t})\), many choices       | i.i.d., CLT, estimator        |
| [2311.03343]         | Mean, \(\mathcal{P}\)-uniform| \(\sqrt{(\Psi^{-1}(1-\alpha)+\log(k/m))/k}\)| finite \(q>2\) moments        |
| [2410.15057]         | SA/SGD, multivariate         | GM, LIL, LIL-ε-Net (\(O(\sqrt{\log t/t})\))| regularity, CLT-type          |
| [2512.13123]         | Projected SGD, convex        | explicit data-dependent suboptimality bound | convexity, sub-G noise, bounded|
| [2302.10108]         | A/B, ratio/lift, streaming   | as above                                   | finite 2+δ moments            |

## 6. Sharpness, Optimality, and Limitations

The term "sharp" AA-CS (see [2502.10380]) refers to sequences for which the coverage is exactly \(1-\alpha\) in the large-\(t\) limit—i.e., the limiting coverage is not conservative. The selection of boundary scaling and normalization constants is critical: the boundary height must match the distributional supremum of the corresponding functional of Brownian motion (e.g., via quantiles of \(\sup_{y>0} |\rho(y) W(y)|\) for a chosen boundary shape \(\rho\)), often requiring numerical calibration.

Optimality is generally achieved in the minimax sense: the boundary widths are of the same order as the fixed-time CLT or LIL rates (\(O(\sqrt{\log t / t})\), down to \(O(\sqrt{(\log\log t)/t})\) for sub-Gaussian or LIL settings) [2210.01948]. Results in [2311.03343] show that under only finite \(q\)-th moment conditions, the AA-CS width is at most a \(\sqrt{\log t}\) factor slower than the best-possible rate.

An essential limitation is that, for small sample sizes, AA-CSs may not provide coverage guarantees (coverage is only asymptotic), in contrast to nonasymptotic CSs, which are necessarily wider but hold for all finite samples. This reflects a trade-off: AA-CSs deliver CLT-style optimal widths and broad applicability, at the expense of finite-sample conservatism.

## 7. Extensions and Current Research Frontiers

AA-CS theory has been extended to a broad range of settings, including:
- **Conditional means and causal parameters**: sequential ATE and LATE estimation with regression adjustments or DML [2408.09598, 2210.08589].
- **Adaptive and contextual bandits**: AA-CSs for ATE and best-arm identification, incorporating sequential regression and variance reduction [2601.00084, 2311.05794].
- **Continuous-time and Poisson processes**: AA-CSs for cumulative rates and arrival intensities [2410.09282].
- **Machine learning and SGD**: uniform certificates for suboptimality, data-dependent stopping, and adaptation to convex (but not strongly convex) objectives [2512.13123].

Recent work has also established AA-CSs with distributional uniformity (valid simultaneously over entire parametric or nonparametric classes) [2311.03343], and explored the connection to optimal sequential tests, minimaxity, and information-theoretic lower bounds.

Open problems include explicit nonasymptotic AA-CSs for stochastic approximation algorithms, rate-optimal AA-CSs under heavy-tailed or dependent data, and adaptive boundaries calibrated to unknown self-normalized variances. Theoretical development continues to focus on balancing sharpness, robustness, and finite-sample validity in ever-higher-dimensional and less regular data regimes.

Source: https://www.emergentmind.com/topics/asymptotic-anytime-valid-confidence-sequences