betaFeedback

WorksMathematics

Sequential anomaly identification with sampling constraints for composite hypotheses

Abstract

We consider the problem of sequential anomaly identification with sampling constraints, where multiple independent data sources are observed over time, but only a limited subset can be sampled at each instant. The objective is to identify the anomalous sources while controlling the probabilities of at least one false alarm and at least one missed detection below prescribed levels. An identification policy must jointly determine when to stop sampling, which sources to declare anomalous, and how to allocate observations across sources under the sampling constraints. We seek policies that minimize the expected time to decision to a first-order asymptotic approximation as the error probabilities vanish. The observations from each source follow an unknown density belonging to one of two disjoint sets, corresponding to regular and anomalous behavior. Focusing on a nonparametric framework, which allows greater flexibility in modeling regular and anomalous statistical behavior, we establish general conditions for asymptotic optimality and provide a unified characterization of asymptotically optimal policies for composite hypothesis testing under sampling constraints. Simulation results illustrate the performance of the proposed policies, and the robustness of the nonparametric framework.

Introduction

In many engineering applications, the goal is to classify a collection of data sources according to their underlying distributions based on sequentially collected measurements. For example, in navigation monitoring systems, one seeks to identify malfunctioning sensors that introduce noise into the measurements [1]. In computer network intrusion detection, deviations from a standard traffic profile, such as a reduced data transmission rate, may indicate a potential attack [2]. In cognitive radio spectrum sensing [3], the objective is to detect available frequency bands where the signal is of very low amplitude. Such applications motivate the study of sequential multiple testing problems for composite hypotheses [4, 5, 6, 7, 8, 9, 10, 11, 12].

Composite hypothesis testing extends the classical binary hypothesis testing framework by replacing two competing distributions with two disjoint sets of distributions. This generalization introduces additional complexity because the true distribution is known only to belong to one of these sets. The study of sequential composite hypothesis testing dates back to Wald [4], who considered a simple null hypothesis against a composite alternative and introduced the Weighted SPRT (WSPRT) and the Generalized SPRT (GSPRT). While the error probabilities of the WSPRT can be controlled using techniques similar to those developed for simple hypotheses, analyzing the GSPRT is more involved. Lorden [13] studied open-ended generalized likelihood ratio tests of a simple null hypothesis against a one-sided composite alternative in exponential families, establishing near-optimal expected sample sizes subject to a bound on the probability of rejecting the null hypothesis. Further asymptotic analyses of sequential tests include the works of Lorden [7], Woodroofe [14], and Chan and Lai [15], the latter focusing on error-probability approximations in multiparameter exponential families. For separate parametric families that need not belong to a common exponential family, Li et al. [16] established logarithmic asymptotic characterizations of the GSPRT’s maximal type I and type II error probabilities, and derived first-order asymptotic expressions for its expected sample size.

The Bayesian formulation of composite hypothesis testing was introduced by Schwarz [6], who proposed a first-order asymptotically Bayes-optimal procedure for parametric families in which the parameter belongs to one of two disjoint sets. Variants of this procedure were subsequently shown to preserve asymptotic optimality [5], [10], [17], and further refinements achieved second-order optimality [7]. Related procedures were also developed in the frequentist setting, where first-order asymptotic optimality was established under appropriate conditions [8]. In a related direction, Yilmaz et al. [18] studied sequential joint detection and estimation, where a decision in favor of the alternative is accompanied by an estimate of a random parameter. They showed that optimal joint performance requires accounting for estimation in the design of the detection rule, rather than optimizing the two tasks separately.

Optimal sequential testing was further extended to experimental design, where the decision maker determines both when to stop and which observations to collect. Chernoff [19] considered a simple null hypothesis against a finite set of alternatives and proposed an asymptotically optimal procedure based on adaptive experiment selection. This framework was subsequently extended to countably infinite alternatives [20] and multiple competing hypotheses [21], [22], with later developments addressing frequentist error criteria [23]. More recently, Deshmukh et al. [24] studied controlled sequential testing of composite hypotheses in exponential family models, with the unknown parameter belonging to one of several prespecified sets. Assuming that the number of available experiments equals the number of hypotheses, they established first order asymptotic optimality using sampling rules inspired by the multi-armed bandit literature [25].

In our work, we consider multiple data sources, each associated with a composite hypothesis testing problem, and adopt a frequentist formulation in which the objective is to minimize the expected stopping time as the error probabilities approach zero. The observations from each source follow a density that belongs to one of two disjoint sets, corresponding to regular and anomalous behavior, respectively. A source is declared anomalous if its underlying density belongs to the latter set. Within exponential family models, the problem of sequential anomaly identification for composite hypotheses has been studied in [26], [27], where all sources are observed at each time and generalized error metrics are considered. The authors propose first-order asymptotically optimal policies and provide explicit characterizations of the optimal performance.

We now consider the nonparametric setting under sampling constraints, where only a subset of sources can be observed at each time due to resource limitations. Nonparametric formulations of sequential hypothesis testing impose minimal assumptions on the underlying distributions and have been studied both in classical settings [28] and, more recently, through time-uniform, nonasymptotic inference methods [29]. These works highlight the inherent difficulty of the problem when the statistical model is not fully specified. In contrast to the existing literature, we consider a setting in which multiple sources must be monitored under explicit sampling constraints. In particular, at each time instant only a subset of sources can be observed, and the goal is to design a policy that jointly determines when to stop, which sources to declare anomalous, and how to allocate observations across sources. The stopping and decision rules must ensure that the error probabilities remain below prescribed levels, while the sampling rule must satisfy the imposed constraint. Existing works on sequential anomaly identification typically assume that all sources are observed at each time or focus on restricted settings. For example, when there is a single anomalous source and only one observation can be collected at each time, asymptotically optimal policies have been derived in [12], [30]. In our formulation, we allow for multiple anomalous sources, simultaneous observations of multiple sources, and more general sampling constraints, expressed in terms of the ratio between the expected number of observations and the expected stopping time. Examples show that accounting for distributional shape beyond parameters is essential for efficient sampling allocation, further motivating the necessity of a nonparametric framework.

We impose regularity conditions on the nonparametric family similar in spirit to those introduced by Pavlov [10 Section 3], who established their validity for multidimensional exponential families under compactness. Within this framework, we establish conditions for consistency and asymptotic optimality of the proposed procedures. In particular, we show that suitable convergence of the test statistics and the estimators ensures these properties. In addition, asymptotic optimality is achieved when the long-run sampling frequency of each source exceeds an explicitly computable threshold. Based on this characterization, we design probabilistic sampling rules that attain the optimal performance. Our results generalize our previous work on sequential anomaly identification for the binary (simple vs. simple) case [31], and establish connections with the multi-armed bandit literature [25, 32, 33, 34, 35]. In classical bandit problems, the objective is to maximize cumulative reward, which requires identifying the arm with the largest mean as quickly as possible [25, 32, 33]. In contrast, in [34], each arm is associated with a composite hypothesis testing problem, and the objective is to minimize the expected stopping time and switching costs. This setting naturally aligns with pure-exploration bandit problems [25, 35], where the goal is to identify a subset of arms satisfying a statistical property. Our results provide a unified characterization of asymptotically optimal sampling strategies across these settings. The proposed framework is also closely connected to recent developments in machine learning that integrate generative models with active learning for anomaly detection [36, 37, 38], highlighting the role of adaptive data acquisition in improving detection performance. However, in these approaches, data acquisition is typically passive, with all features or data streams observed uniformly over time. In contrast, our formulation explicitly incorporates sampling constraints and enables the sequential allocation of observations to the most informative sources, providing a principled approach to active anomaly detection under resource constraints.

The remainder of the paper is organized as follows. Section II introduces the problem formulation, Section IV provides an illustrative example, and § 5 derives a universal asymptotic lower bound (UALB) on the expected stopping time. Section VI presents a family of policies, and § 7 establishes conditions under which an appropriately designed policy attains the UALB and is therefore asymptotically optimal. Sections VIII and IX present test statistics and estimators that satisfy the required asymptotic conditions. § 10 and XI evaluate the performance of the proposed policy through simulation studies. Finally, Section XII concludes the paper and outlines directions for future research.

We end this section with some notations we use throughout the paper. We use :=:= to indicate the definition of a new quantity and ≡\equiv to indicate a duplication of notation. We set N:={1,2,…}\mathbb{N} := \{1,2,\ldots\} and [n]:={1,…,n}[n] := \{1,\ldots,n\} for n∈Nn \in\mathbb{N}, we denote by ∣A∣|A| the size and by 2A2^{A} the powerset of a set AA, by [a][a] the floor and by ⌈a⌉\lceil a\rceil the ceiling of a positive number aa, and by 1\mathbf{1} the indicator of an event. The symbol ∨\vee stands for the maximum, and the symbol ∧\wedge for the minimum of two quantities. We write x∼yx\sim y when lim⁡(x/y)=1\lim(x/y)=1, x≳yx\gtrsim y when lim inf⁡(x/y)≥1\liminf(x/y)\ge1, and x≲yx\lesssim y when lim sup⁡(x/y)≤1\limsup(x/y)\le1, where the limit is taken in some sense that will be specified. We denote by ∥⋅∥p\|\cdot\|_p the LpL^p-norm of a function. Moreover, iid stands for independent and identically distributed, and we say that a sequence of positive numbers (an)(a_n) is summable if ∑n=1∞an<∞\sum_{n=1}^{\infty}a_n<\infty and exponentially decaying if there are real numbers c,d>0c,d>0 such that an≤cexp⁡{−dn}a_n\le c\exp\{-dn\} for every n∈Nn\in\mathbb{N}. A useful property is that if (an)(a_n) is exponentially decaying, so is the sequence (∑m≥ζnam)(\sum_{m\ge\zeta n}a_m), for any ζ∈(0,1]\zeta\in(0,1].

Problem formulation

Let (S,S)(\mathcal{S},\mathcal{S}) be a measurable space, and let (Ω,F,P)(\Omega,\mathcal{F},\mathbb{P}) be a probability space on which are defined MM independent sequences of iid S\mathcal{S}-valued random elements, {Xi(n):n∈N}\{X_i(n):n\in\mathbb{N}\}, i∈[M]i\in[M], corresponding to MM distinct data sources. In addition, let {Zi(n):n∈N}\{Z_i(n):n\in\mathbb{N}\}, i∈[M]i\in[M], be MM independent sequences of iid Uniform[0,1][0,1] random variables, used for randomization purposes, and define Z(n):=(Z1(n),…,ZM(n))Z(n):=(Z_1(n),\ldots,Z_M(n)).

For each i∈[M]i\in[M], the observations {Xi(n):n∈N}\{X_i(n):n\in\mathbb{N}\} are generated according to a density fi∈Φif_i\in\Phi_i, with respect to a σ\sigma-finite measure νi\nu_i, where the class of densities Φi\Phi_i is equipped with the L1L^1-norm ∥⋅∥1\|\cdot\|_1. We say that source ii is anomalous if fi∈Φi1f_i\in\Phi_i^1, and regular if fi∈Φi0f_i\in\Phi_i^0, where Φi:=Φi0∪Φi1\Phi_i:=\Phi_i^0\cup\Phi_i^1 and Φi0∩Φi1=∅\Phi_i^0\cap\Phi_i^1=\varnothing. Let Φ:=Φ1×⋯×ΦM\Phi:=\Phi_1\times\cdots\times\Phi_M denote the product space. For each A⊆[M]A\subseteq[M], define

ΦA:={(g1,…,gM):gi∈Φi1 for i∈A, and gj∈Φj0 for j∉A}.\Phi_A:=\{(g_1,\ldots,g_M):g_i\in\Phi_i^1\text{ for }i\in A,\text{ and }g_j\in\Phi_j^0\text{ for }j\notin A\}.

where AA stands for the subset of anomalous sources. For each A⊆[M]A\subseteq[M] and f:=(f1,…,fM)∈ΦAf:=(f_1,\ldots,f_M)\in\Phi_A, we denote by Pf\mathbb{P}_f the probability measure and by Ef\mathbb{E}_f the corresponding expectation, when the underlying true densities are given by ff. When the dependence on ff is not essential for our computations, we simply write P\mathbb{P} and E\mathbb{E}.

For each i∈[M]i\in[M] and g∈Φig\in\Phi_i, we define the Kullback–Leibler (KL) divergence

D(fi,g):=Efi[log⁡(fi(Xi)g(Xi))].D(f_i,g):=\mathbb{E}_{f_i}\left[\log\left(\frac{f_i(X_i)}{g(X_i)}\right)\right].

where XiX_i denotes a generic observation from source ii. We impose the following assumptions, which are required for the development of our results:

(i) Separation of hypotheses:

Ii(fi):=inf⁡g∈Φi0D(fi,g)∈(0,∞),∀i∈A,(1)I_i(f_i):=\inf_{g\in\Phi_i^0}D(f_i,g)\in(0,\infty),\qquad\forall i\in A, \tag*{(1)}
Ji(fi):=inf⁡g∈Φi1D(fi,g)∈(0,∞),∀i∉A.(2)J_i(f_i):=\inf_{g\in\Phi_i^1}D(f_i,g)\in(0,\infty),\qquad\forall i\notin A. \tag*{(2)}

(ii) Continuity of the infimum maps:

lim⁡f→fiIi(f)=Ii(fi),lim⁡f→fiJi(f)=Ji(fi).(3)\lim_{f\to f_i} I_i(f)=I_i(f_i),\qquad\lim_{f\to f_i} J_i(f)=J_i(f_i). \tag*{(3)}

Both assumptions depend on the true density fif_i, which is unknown, and thus it is required that they hold locally for every fi∈Φif_i\in\Phi_i, i.e., in a neighborhood of fif_i.

The main objective is to identify the set of anomalous sources AA, i.e., to determine whether fi∈Φi1f_i\in\Phi_i^1 or fi∈Φi0f_i\in\Phi_i^0 for each i∈[M]i\in[M], based on sequential observations under sampling constraints that preclude observing all sources at every time. To this end, we consider policies that consist of three components: (i) a stopping time TT, (ii) a sequence Δ:={Δ(n):n∈N}\Delta:=\{\Delta(n):n\in\mathbb{N}\}, where Δ(n)⊆[M]\Delta(n)\subseteq[M] denotes the current estimate of the anomalous set and Δ(T)\Delta(T) is the final decision, and (iii) a sequence R:={R(n):n∈N}R:=\{R(n):n\in\mathbb{N}\}, where R(n)⊆[M]R(n)\subseteq[M] is the set of sources sampled at time nn. We say that RR is a sampling rule if R(n)R(n) is Fn−1R\mathcal{F}_{n-1}^R-measurable for every n∈Nn\in\mathbb{N}, where the filtration {FnR:n∈N}\{\mathcal{F}_n^R:n\in\mathbb{N}\} is defined recursively by

FnR:=σ(Fn−1R,Z(n),{Xi(n):i∈R(n)}),n∈N,\mathcal{F}_n^R:=\sigma\bigl(\mathcal{F}_{n-1}^R,Z(n),\{X_i(n):i\in R(n)\}\bigr),\qquad n\in\mathbb{N},
F0R:=σ(Z(0)).\mathcal{F}_0^R:=\sigma(Z(0)).

A triplet (R,T,Δ)(R,T,\Delta) is called a policy if RR is a sampling rule, TT is a stopping time with respect to {FnR:n∈N}\{\mathcal{F}_n^R:n\in\mathbb{N}\}, i.e., {T=n}∈FnR\{T=n\}\in\mathcal{F}_n^R for all nn, and Δ(n)\Delta(n) is FnR\mathcal{F}_n^R-measurable for every n∈Nn\in\mathbb{N}. In this case, we refer to TT as the stopping rule and to Δ\Delta as the decision rule. Our policies (R,T,Δ)(R,T,\Delta) must satisfy prescribed error and sampling constraints, described next.

Error constraints: Let α,β∈(0,1)\alpha,\beta\in(0,1). A policy (R,T,Δ)(R,T,\Delta) is said to belong to the class C(α,β)\mathcal{C}(\alpha,\beta) if it satisfies the error constraints

References

  1. [1]I. Nikiforov, V. Varavva, and V. Kireichikov, “Application of statistical fault detection algorithms to navigation systems monitoring,” Automatica, vol. 29, no. 5, pp. 1275–1290, 1993.DOI
  2. [2]A. G. Tartakovsky, B. L. Rozovskii, R. B. Blažek, and H. Kim, “Detection of intrusions in information systems by sequential change-point methods,” Statistical methodology, vol. 3, no. 3, pp. 252–293, 2006.DOI
  3. [3]J. Font-Segura and X. Wang, “Glrt-based spectrum sensing for cognitive radio with prior information,” IEEE Transactions on Communications, vol. 58, no. 7, pp. 2137–2146, 2010.
  4. [4]A. Wald, Sequential analysis. Courier Corporation, 2004.
  5. [5]S. P. Wong, “Asymptotically optimum properties of certain sequential tests,” The Annals of Mathematical Statistics, pp. 1244–1263, 1968.DOI
  6. [6]G. Schwarz, “Asymptotic shapes of bayes sequential testing regions,” The Annals of mathematical statistics, pp. 224–236, 1962.DOI
  7. [7]G. Lorden, “Nearly-optimal sequential tests for finitely many parameter values,” The Annals of Statistics, vol. 5, no. 1, pp. 1–21, 1977.DOI
  8. [8]T. L. Lai, “Nearly optimal sequential tests of composite hypotheses,” The Annals of Statistics, pp. 856–886, 1988.DOI
  9. [9]H. Robbins and D. Siegmund, “The expected sample size of some tests of power one,” The Annals of Statistics, vol. 2, no. 3, pp. 415–436, 1974.DOI
  10. [10]I. V. Pavlov, “Sequential procedure of testing composite hypotheses with applications to the kiefer–weiss problem,” Theory of Probability & Its Applications, vol. 35, no. 2, pp. 280–292, 1991.DOI
  11. [11]T. Gafni, B. Wolff, G. Revach, N. Shlezinger, and K. Cohen, “Anomaly search over discrete composite hypotheses in hierarchical statistical models,” IEEE Transactions on Signal Processing, vol. 71, pp. 202–217, 2023.DOI
  12. [12]B. Hemo, T. Gafni, K. Cohen, and Q. Zhao, “Searching for anomalies over composite hypotheses,” IEEE Transactions on Signal Processing, vol. 68, pp. 1181–1196, 2020.DOI
  13. [13]G. Lorden, “Open-ended tests for koopman-darmois families,” The Annals of Statistics, pp. 633–643, 1973.DOI
  14. [14]M. Woodroofe, Nonlinear renewal theory in sequential analysis. SIAM, 1982.
  15. [15]H. P. Chan and T. L. Lai, “Asymptotic approximations for error probabilities of sequential or fixed sample size tests in exponential families,” Annals of statistics, pp. 1638–1669, 2000.DOI
  16. [16]X. Li, J. Liu, and Z. Ying, “Generalized sequential probability ratio test for separate families of hypotheses,” Sequential analysis, vol. 33, no. 4, pp. 539–563, 2014.pubmed.ncbi.nlm.nih.gov/27418716
  17. [17]J. Kiefer and J. Sacks, “Asymptotically optimum sequential inference and design,” The Annals of Mathematical Statistics, pp. 705–750, 1963.
  18. [18]Y. Yilmaz, G. V. Moustakides, and X. Wang, “Sequential joint detection and estimation,” Theory of Probability & Its Applications, vol. 59, no. 3, pp. 452–465, 2015.
  19. [19]H. Chernoff, “Sequential design of experiments,” Ann. Math. Statist., vol. 30, no. 3, pp. 755–770, 09 1959. [Online]. Available: http://dx.doi.org/10.1214/aoms/1177706205
  20. [20]A. E. Albert, “The Sequential Design of Experiments for Infinitely Many States of Nature,” The Annals of Mathematical Statistics, vol. 32, no. 3, pp. 774 – 799, 1961. [Online]. Available: https://doi.org/10.1214/aoms/1177704973
  21. [21]S. A. Bessler, “Theory and applications of the sequential design of experiments, k-actions and infinitely many experiments, part i theory.” Department of Statistics, Stanford University, Technical Report 55, 1960.
  22. [22]——, “Theory and applications of the sequential design of experiments, k-actions and infinitely many experiments, part ii applications.” Department of Statistics, Stanford University, Technical Report 56, 1960.
  23. [23]S. Nitinawarat, G. K. Atia, and V. V. Veeravalli, “Controlled sensing for multihypothesis testing,” IEEE Transactions on Automatic Control, vol. 58, no. 10, pp. 2451–2464, 2013.arxiv.org/abs/1205.0858
  24. [24]A. Deshmukh, V. V. Veeravalli, and S. Bhashyam, “Sequential controlled sensing for composite multihypothesis testing,” Sequential Analysis, vol. 40, no. 2, pp. 259–289, 2021.arxiv.org/abs/1910.12697
  25. [25]A. Garivier and E. Kaufmann, “Optimal best arm identification with fixed confidence,” in Conference on Learning Theory. PMLR, 2016, pp. 998–1027.
  26. [26]Y. Song and G. Fellouris, “Sequential multiple testing with generalized error control: An asymptotic optimality theory,” The Annals of Statistics, vol. 47, no. 3, pp. 1776 – 1803, 2019. [Online]. Available: https://doi.org/10.1214/18-AOS1737
  27. [27]——, “Supplementary file to: Sequential multiple testing with generalized error control: An asymptotic optimality theory,” The Annals of Statistics, vol. 47, no. 3, pp. 1776 – 1803, 2019. [Online]. Available: https://doi.org/10.1214/18-AOS1737
  28. [28]D. A. Darling and H. Robbins, “Some nonparametric sequential tests with power one,” Proceedings of the National Academy of Sciences, vol. 61, no. 3, pp. 804–809, 1968.pubmed.ncbi.nlm.nih.gov/16591711
  29. [29]S. R. Howard, A. Ramdas, J. McAuliffe, and J. Sekhon, “Time-uniform, nonparametric, nonasymptotic confidence sequences,” The Annals of Statistics, vol. 49, no. 2, pp. 1055–1080, 2021.DOI
  30. [30]N. K. Vaidhiyan and R. Sundaresan, “Learning to detect an oddball target,” IEEE Transactions on Information Theory, vol. 64, no. 2, pp. 831–852, 2018.arxiv.org/abs/1508.05572
  31. [31]A. Tsopelakos and G. Fellouris, “Sequential anomaly detection under sampling constraints,” IEEE Transactions on Information Theory, 2022.
  32. [32]T. L. Lai and H. Robbins, “Asymptotically efficient adaptive allocation rules,” Advances in applied mathematics, vol. 6, no. 1, pp. 4–22, 1985.DOI
  33. [33]Anantharam, P. Varaiya, and J. Walrand, “Asymptotically efficient allocation rules for the multiarmed bandit problem with multiple plays-part i: Iid rewards,” IEEE Transactions on Automatic Control, vol. 32, no. 11, pp. 968–976, 1987.DOI
  34. [34]G. R. Prabhu, S. Bhashyam, A. Gopalan, and R. Sundaresan, “Sequential multi-hypothesis testing in multi-armed bandit problems: An approach for asymptotic optimality,” IEEE Transactions on Information Theory, 2022.arxiv.org/abs/2007.12961
  35. [35]S. Bubeck, R. Munos, and G. Stoltz, “Pure exploration in multi-armed bandits problems,” in International conference on Algorithmic learning theory. Springer, 2009, pp. 23–37.DOI
  36. [36]Y. Liu, Z. Li, C. Zhou, Y. Jiang, J. Sun, M. Wang, and X. He, “Generative adversarial active learning for unsupervised outlier detection,” IEEE Transactions on Knowledge and Data Engineering, vol. 32, no. 8, pp. 1517–1528, 2019.arxiv.org/abs/1809.10816
  37. [37]T. Schlegl, P. Seeböck, S. M. Waldstein, G. Langs, and U. Schmidt-Erfurth, “f-anogan: Fast unsupervised anomaly detection with generative adversarial networks,” Medical image analysis, vol. 54, pp. 30–44, 2019.DOI
  38. [38]L. Ruff, J. R. Kauffmann, R. A. Vandermeulen, G. Montavon, W. Samek, M. Kloft, T. G. Dietterich, and K.-R. Müller, “A unifying review of deep and shallow anomaly detection,” Proceedings of the IEEE, vol. 109, no. 5, pp. 756–795, 2021.DOI
  39. [39]A. Tartakovsky, I. Nikiforov, and M. Basseville, Sequential analysis: Hypothesis testing and changepoint detection. CRC press, 2014.
  40. [40]A. W. Van der Vaart, Asymptotic statistics. Cambridge university press, 2000, vol. 3.
  41. [41]U. Grenander, “On the theory of mortality measurement: part ii,” Scandinavian Actuarial Journal, vol. 1956, no. 2, pp. 125–153, 1956.DOI
  42. [42]A. Tsopelakos and G. Fellouris, “Sequential anomaly identification under sampling constraints for generalized error metrics,” IEEE Transactions on Information Theory, 2025.DOI
  43. [43]S. Nitinawarat and V. V. Veeravalli, “Controlled sensing for sequential multihypothesis testing with controlled markovian observations and non-uniform control cost,” Sequential Analysis, vol. 34, no. 1, pp. 1–24, 2015.arxiv.org/abs/1310.1844
  44. [44]T. Lambez and K. Cohen, “Anomaly search with multiple plays under delay and switching costs,” IEEE Transactions on Signal Processing, vol. 70, pp. 174–189, 2021.DOI
  45. [45]H. Scheffé, “A useful convergence theorem for probability distributions,” The Annals of Mathematical Statistics, vol. 18, no. 3, pp. 434–438, 1947.DOI
  46. [46]J. R. Munkres, Topology, 2nd ed. Prentice Hall, 2000.
  47. [47]W. Rudin, Principles of Mathematical Analysis, 3rd ed. McGraw-Hill, 1976.
  48. [48]P. Billingsley, Convergence of probability measures. wiley, New York, 1999, vol. 2.
  49. [49]P. Hall and C. C. Heyde, “Martingale limit theory and its application,” Probability and Mathematical Statistics. New York etc.: Academic Press, A Subsidiary of Harcourt Brace Jovanovich, Publishers. XII, 308 p. $ 36.00 (1980)., 1980.
  50. [50]G. H. Hardy, J. E. Littlewood, and G. Pólya, Inequalities. Cambridge university press, 1988.

Paper details

vlnc:W_shzjeenw
Version
v1 · latest
Published
Fresh — added to the Hub within the last 30 days
Added
License
CC BY 4.0
Usage

views · 7

downloads · 0

A view counts once per browser per day, a download each time the PDF is requested.

  • Mathematics

Not recorded for this paper

View statement
Looking for related papers…
Contents