Pith. sign in

REVIEW 6 minor 47 references

A robust scan statistic for high-dimensional change-point detection is shown to converge to a Gaussian process with covariance kernel K0(s,r)=ψ(s,r)^2/(ψ(s)ψ(r)), enabling asymptotically exact calibration and consistent multiple-break local

Reviewed by Pith at T0; open to challenge. T0 means a machine referee read the full paper against a public rubric. the ladder, T0–T4 →

Challenge this review Re-run · record.json Download PDF Read on arXiv ↗

T0 review · deepseek-v4-flash

2026-08-01 05:39 UTC pith:OSG5BETJ

load-bearing objection ERHT is a substantial, carefully derived contribution to robust high-dimensional change-point testing; the flagged t_3 moment issue is a false alarm, and the real caveats are implementation-level rather than mathematical.

arxiv 2607.22162 v1 pith:OSG5BETJ submitted 2026-07-24 stat.ME

Elliptical Regularized Hotelling Tests for High-Dimensional Change-Point Detection

Fengyi Song , Mengtao Wen , Long Feng This is my paper
classification stat.ME MSC 62H1562G1062G20
keywords change-point detectionhigh-dimensional location testingelliptical distributionspatial medianspatial-sign covarianceridge regularizationGaussian-process limitCauchy aggregation
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved

The pith

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper proposes ERHT, a two-sample scan test for location changes in high-dimensional elliptical sequences. It contrasts spatial medians of adjacent segments and standardizes the contrast by a ridge-regularized inverse of the pooled centered spatial-sign covariance matrix. The main claim is that the studentized scan process converges to a centered Gaussian process whose covariance kernel is a squared overlap of temporal contrast functions, with joint convergence across a grid of ridge parameters. That limit yields asymptotically exact critical values via the supremum distribution and a Cauchy aggregation rule, plus local power and localization rates, and a wild-binary-segmentation extension that consistently estimates the number and locations of multiple breaks. If correct, the method gives valid p-values in the heavy-tailed, cross-sectionally dependent high-dimensional regime.

Core claim

For each candidate scan interval s=(t1,t2,t3), the statistic Z_ρ(s) compares spatial medians of two adjacent windows after studentization by a ridge-regularized inverse of the spatial-sign covariance matrix. The paper proves that over the single-change scan {(0,t,1)} and the multiple-change scan {t1<t2<t3} the process {Z_ρ(s)} converges to a centered Gaussian process with covariance K0(s,r)=ψ(s,r)^2/(ψ(s)ψ(r)), where ψ(s,r) is the L^2 overlap of the two temporal contrast functions. Joint convergence over the ridge grid holds with cross-parameter correlation r_E(ρ,ρ'), and because the marginal law is ρ-independent under the common full-sample pool, the same supremum calibration applies at eve

What carries the argument

The companion-matrix representation V_raw ≈ m β^⊤ A_ρ β combined with a Rademacher sign representation reduces the nonlinear spatial-median contrast to a conditionally quadratic form in independent signs. This gives explicit centering κ and variance σ², and the deterministic-equivalent resolvent D_ρ,n = (a_ρ,n Ω_p + ρI)^{-1} from the Marchenko-Pastur fixed point transfers the cross-sectional geometry to the covariance kernel K0(s,r)=ψ(s,r)²/(ψ(s)ψ(r)) and the cross-ridge correlation r_E(ρ,ρ').

Load-bearing premise

Assumption 3.1 requires the inverse radial variable ξ=R^{-1} to satisfy E ξ^{4+η}<∞ for some η>0 along with a polylogarithmic maximum bound; every uniform expansion in the proof chain depends on this moment margin, and the paper's flagship multivariate t_3 heavy-tailed design violates it because for t_ν, E ξ^r is finite only for r<ν.

What would settle it

Simulate the ERHT single-change scan under multivariate t_3 errors with p/n≈γ and no change, compute Gaussian-supremum-calibrated p-values from F_sc, and check empirical size: if the convergence theorems were valid under t_3, rejection rates would approach α; if, as the moment gap suggests, rates deviate systematically as n,p grow, the theorems' hypotheses are not met. Equivalently, compute E(R^{-1})^{4+η} for t_3 to see it is infinite for every η>0.

Watch this falsifier — get emailed when new claim-graph text bears on it.

If this is right

  • P-values from F_S are asymptotically uniform under H0, so Gaussian-supremum calibration of ERHT is valid for fixed p/n and elliptical heavy-tailed errors.
  • The single-change test has non-trivial local power at n^{-1/4} shifts whose spectral signal measure converges, and strong consistency when √n‖Δ‖²→∞.
  • The estimated break location converges at rate O_P(s_{n,ρ}^{-1}+e_{σ,n}), and if s_{n,ρ}e_{σ,n}=O(1), at rate O_P(s_{n,ρ}^{-1}).
  • WBS-ERHT consistently selects the number of breaks and localizes them with maximum normalized error O_P(t_WBS/(√n min_j‖Δ_j‖²)).
  • The ridge grid can be aggregated by the analytic Cauchy rule with exact limiting rejection probability determined by the joint Gaussian law, not by assuming the Cauchy p-value is uniform.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • Because the common-pool assumption makes the marginal Gaussian law independent of ρ, the paper's calibration step implicitly turns the choice of ridge parameter into a nuisance; one could extend the same aggregation to a continuum of ρ values, or to maximum-type combinations, with the same limit theory.
  • The radial moment condition E ξ^{4+η}<∞ is the point most likely to fail in practice: for multivariate t_ν, E ξ^r is finite only when r<ν, so the showcased t_3 design does not satisfy Assumption 3.1 as stated. The supplementary verification in Section S1.1 claims every fixed-ν t_ν satisfies the condition; that claim conflicts with the moment bound E D_ν^r < ∞ for r<ν.
  • The covariance kernel's temporal factor depends only on interval fractions, not on the shape matrix, so different elliptical models are absorbed into the scalar variance and cross-ridge correlation; this suggests the null distribution of the supremum is universal within a fixed Euclidean structure, a feature worth testing for data with non-elliptical directional distributions.
  • For serially dependent observations, the permutation calibration used in the empirical section is no longer exact; the theory's independence assumption is the main obstacle to applying ERHT to time series with autocorrelation.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit.

Referee Report

0 major / 6 minor

Summary. The paper proposes an elliptical regularized Hotelling (ERHT) procedure for high-dimensional location change-point detection under heavy-tailed, cross-sectionally dependent elliptical observations. The statistic contrasts spatial medians of adjacent segments and studentizes the contrast using a ridge-regularized inverse of the pooled centered spatial-sign covariance matrix. The main theoretical results are: (i) uniform raw-to-score reduction and pointwise null laws (Prop. 3.1, Thm. 3.1); (ii) Gaussian-process limits for the single- and multiple-change scan statistics with covariance kernel K0(s,r)=ψ(s,r)^2/(ψ(s)ψ(r)) (Thms. 3.2, 3.7); (iii) joint convergence over a finite ridge grid with cross-parameter correlation r_E(ρ,ρ') (Thms. 3.3, 3.8), yielding exact asymptotic calibration of the Cauchy-aggregated test (Thms. 3.4, 3.9); (iv) local power and localization rates for single-change alternatives (Thms. 3.5, 3.6); and (v) WBS-ERHT consistency for estimating the number and locations of multiple changes (Thm. 4.1). Simulations compare ERHT with covariance-based RHT, mean-based DMS0, and spatial-sign SSCPD0 across normal, t3, and Gaussian-mixture errors; a Fama–French 49 industry portfolio analysis reports four structural breaks.

Significance. If the theorem chain holds, the paper makes a substantial contribution: it extends regularized Hotelling methodology to heavy-tailed elliptical data in the proportional-growth regime, provides explicit Gaussian-process covariance kernels and joint-limit calibration, and gives a complete WBS consistency theory with localization rates. The strengths are the detailed supplementary proof chain, the use of deterministic equivalents and companion laws derived from first principles, and the honest distinction between exact joint-limit calibration and the analytic Cauchy rule. I specifically checked the concern that the t3 simulation design violates Assumption 3.1. That concern is based on a sign error: for S_ν ~ χ²_ν, E(S_ν)^t is finite for every positive t, so Eξ^{4+η} is finite for the multivariate t3 construction; the verification in S1.1 is correct. The main practical caveat is that the analytic Cauchy transformation used in the numerical sections is characterized but not proven to control the asymptotic level; this does not undermine the central Gaussian-process or WBS theorems, but it should be stated more prominently.

minor comments (6)
  1. [Section 2.3 and Theorems 3.4/3.9] The numerical method called ERHT-CC in Sections 5 and 6 uses the analytic Cauchy transformation, but Theorems 3.4 and 3.9 only characterize its limiting rejection probability as P{T_∞ ≥ cot(πα)}; they do not establish that this is ≤ α under the dependence among the P_k's. The exact joint-limit calibration is a theoretical option but is not implemented in the experiments. Please state this limitation explicitly where ERHT-CC is defined and used, so that readers do not treat the analytic P_CC as an exact p-value.
  2. [Section 6.1] The statement that subtracting the coordinatewise full-sample mean 'has no effect on either segment contrasts or centered spatial signs' is imprecise: subtracting a random vector changes the origin used for spatial signs, and coordinatewise demeaning by a data-dependent mean can break the exact elliptical symmetry assumed by the model. Please rephrase to say that the mean shift does not affect the difference between segment mean contrasts, or provide a formal justification for the preprocessing within the elliptical model.
  3. [Section 4.2, Eq. (24) and Assumption 4.2] The notation for the maximum and minimum jump signal, s_WBS and ̲s_WBS, is easy to confuse in both Eq. (24) and Assumption 4.2. Please use distinct symbols consistently throughout the statements and proofs.
  4. [Table 1] Some ERHT-CC empirical sizes are noticeably above the nominal 5% level, e.g., Identity/Normal/p=400/n=200 shows 8.1%. A brief comment on finite-sample calibration, or additional Monte Carlo replications, would help the reader assess whether this is sampling noise or a small-sample bias.
  5. [Figures 4-6] The panel label 'Ploy' appears in multiple-change power figures; it should read 'Poly'.
  6. [General] Please include a data/code availability statement. The Fama–French data are public, but the exact preprocessing steps, permutation scheme, and tuning choices should be documented for reproducibility.

Circularity Check

0 steps flagged

No significant circularity: the Gaussian-process limits, cross-ridge correlations, and WBS consistency are derived from stated primitive assumptions without fitting data or importing a load-bearing self-citation.

full rationale

The central derivation chain is self-contained. The limiting kernel K0(s,r)=ψ(s,r)^2/(ψ(s)ψ(r)) is computed explicitly from the ordinary CUSUM temporal contrast (Lemma 16 of the supplement), not reverse-engineered from the statistic's finite-sample output. The cross-ridge correlation r_E(ρ,ρ') is obtained from a companion random-matrix limit c_{ρ,ρ'}(c_pool) (Lemma 9, formulas S41-S42), again from first principles under Assumptions 3.1-3.3. The variance proxy σ_ρ^2 = 2ζ^{-4} c_{ρ,ρ} is a deterministic limit, not a fitted parameter. Nothing in Theorems 3.1-3.9 calibrates to data: the Gaussian-supremum distribution F_S is defined as the law of a limiting supremum and then proven to be the joint limit through the process convergence results. The Cauchy aggregation theorem (3.4/3.9) explicitly characterizes the limiting rejection probability of the analytic transformation rather than assuming uniformity, so it does not smuggle in the target calibration. WBS consistency (Theorem 4.1) is proved from geometric isolation, population separation, and deterministic signal/threshold bounds; the threshold and window parameters are tuning inputs, not fitted predictions. The paper's self-citations (e.g., Liu et al. 2025, Zhao et al. 2026) are used for context or comparison, not as the proof of any central theorem. The reader's stated t_3 concern is not a circularity concern and is in fact mistaken: for S_ν ~ χ^2_ν, E(S_ν)^t = 2^t Γ(t+ν/2)/Γ(ν/2) is finite for every t>0, so the radial moment condition E ξ^{4+η}<∞ holds for the t_3 design and the supplement's verification is correct. Even if an assumption were violated, that would be a correctness gap, not circular equivalence between inputs and outputs. No step reduces by construction to its own input, and no 'prediction' is a renamed fitted quantity.

Axiom & Free-Parameter Ledger

4 free parameters · 7 axioms · 0 invented entities

Everything the central theorems require beyond the elliptical model is stated in Assumptions 3.1-3.3 and 4.1-4.2. Tuning quantities (ridge grid, equal Cauchy weights, WBS threshold 2.5, M_n=200) are hand-chosen rather than fitted. Derivations import standard machinery: negative-axis deterministic equivalents (Hachem et al. 2007/2013; Bai-Silverstein 2010), de Jong's quadratic-form CLT, Hanson-Wright, Haar integration, spatial-median expansions (Oja 2010; Magyar-Tyler 2011; Li and Xu 2022). No invented entities. The fragile axiom is the (4+eta)-moment condition in Assumption 3.1 versus the t_3 simulations (Section 5), as detailed in S1.1.

free parameters (4)
  • Ridge regularization grid rho/gamma = {0.05, 0.10, ..., 0.50} * gamma
    Hand-chosen grid for the adaptive Cauchy aggregation; theory (Assumption 3.3) only requires a fixed compact grid bounded away from 0, so endpoints and spacing are tuning choices, not data-fitted constants.
  • Cauchy combination weights w_k = 1/K (equal)
    Equal weights chosen by hand; Theorem 3.4 only requires positive weights summing to 1.
  • WBS-ERHT tuning constants = t_WBS = 2.5, M_n = 200, epsilon = 0.1, plus m_min, g_n, h_n
    Used in the Fama-French segmentation (Section 6.3); the consistency theory (Assumption 4.2) imposes a hierarchy on these rather than fixing them.
  • Simulation signal strengths c_sig = setting-dependent (e.g., 2-30 in Gaussian panels)
    Selected in two stages via preliminary ERHT runs so curves span a broad power range; the same values are reused for all methods, so this is a display choice, not a model parameter.
axioms (7)
  • domain assumption Elliptical error model (1) with radial regularity in Assumption 3.1 (E xi -> zeta^{-1} in (0,infinity); limsup E xi^{4+eta} < infinity; P(max xi_i > (log n)^{c0}) -> 0)
    Underpins spatial-median Bahadur-type expansions and uniform sign-based remainder bounds. Note: multivariate t_3 (Section 5) violates the (4+eta) moment condition, and S1.1's verification is incorrect.
  • domain assumption Assumption 3.2: p/n -> gamma in (0,infinity); uniform upper spectral bound lambda_{j,p} <= omega+; ESD of Omega_p converges to H
    Establishes the Marcenko-Pastur / deterministic-equivalent machinery (Lemmas 1, 8-9) that produces r_E and the variance limits.
  • domain assumption Assumption 3.3: finite ridge grid in a compact interval [rho0, rho1] subset (0,infinity)
    Keeps Q_{rho,s} stably invertible; the theory does not cover the rho -> 0 (unregularized) limit used by the SSCPD0 comparator.
  • domain assumption Assumption 3.4: local signal Delta = n^{-1/4} d with spectral signal measure converging to G_Delta; strong signals with l_n||Delta|| -> 0 and sqrt(n)||Delta||^2 -> infinity
    Defines the power and localization regimes that Theorems 3.5-3.6 are stated for.
  • ad hoc to paper Assumptions 4.1-4.2: random WBS intervals with delta_min < (1-2epsilon)delta_R and delta_R + delta_min < delta_0/2; jump/tuning hierarchy t_WBS = o(s_WBS), sqrt(log n) + s_WBS e_WBS = o(t_WBS), and deletion-radius hierarchy
    Sufficient conditions engineered for the induction proof of Theorem 4.1 (Lemmas 21-24); they constrain tuning rather than emerging from the model.
  • standard math Standard RMT/CLT imports: negative-axis deterministic equivalents (Hachem et al. 2007, 2013; Bai-Silverstein 2010; Silverstein-Choi 1995), de Jong (1987) quadratic-form CLT, Hanson-Wright concentration, Haar-integral formulas
    Used in Lemmas 1, 8-9, 15, 18 without proof.
  • standard math Spatial-median asymptotic expansion results (Oja 2010; Magyar-Tyler 2011; Li and Xu 2022)
    Basis for the score-equation / Bahadur form of the spatial median used in Lemma 7.

pith-pipeline@v1.3.0-alltime-deepseek · 73331 in / 38253 out tokens · 358509 ms · 2026-08-01T05:39:25.666506+00:00 · methodology

0 comments
read the original abstract

We propose an elliptical regularized Hotelling (ERHT) procedure for detecting location changes in high-dimensional sequences with heavy-tailed, cross-sectionally dependent observations. ERHT contrasts spatial medians on adjacent segments using a ridge-regularized inverse of the pooled centered spatial-sign covariance matrix, thereby combining robustness to radial variation with dependence-aware weighting. We establish Gaussian-process limits for the single- and multiple-change scans and joint convergence over a finite set of regularization parameters. These results provide asymptotically exact calibration of a Cauchy-aggregated adaptive test through the joint Gaussian limit, together with guarantees for local power and single-change localization. We further embed the ERHT score in wild binary segmentation and prove consistency for estimating the number and locations of multiple changes. Simulations show that ERHT is generally well calibrated and delivers competitive power under heavy-tailed distributions, particularly when cross-sectional dependence is substantial. An analysis of the Fama--French 49 industry portfolios reveals persistent evidence of location instability and identifies four structural breaks.

Figures

Figures reproduced from arXiv: 2607.22162 by Fengyi Song, Long Feng, Mengtao Wen.

Figure 1
Figure 1. Figure 1: Size-corrected empirical power under Gaussian errors with [PITH_FULL_IMAGE:figures/full_fig_p016_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Size-corrected empirical power under multivariate [PITH_FULL_IMAGE:figures/full_fig_p017_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Size-corrected empirical power under Gaussian-mixture errors with [PITH_FULL_IMAGE:figures/full_fig_p019_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Size-corrected empirical power of the multiple-change global tests under Gaussian [PITH_FULL_IMAGE:figures/full_fig_p022_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Size-corrected empirical power of the multiple-change global tests under variance [PITH_FULL_IMAGE:figures/full_fig_p023_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Size-corrected empirical power of the multiple-change global tests under variance [PITH_FULL_IMAGE:figures/full_fig_p024_6.png] view at source ↗

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

47 extracted references · 1 linked inside Pith

  1. [1]

    Baranowski, R., Chen, Y., and Fryzlewicz, P. (2019). Narrowest-over-threshold detection of multiple change points and change-point-like features. Journal of the Royal Statistical Society: Series B 81, 649--672

    2019

  2. [2]

    Boucheron, S., Lugosi, G., and Massart, P. (2013). Concentration Inequalities: A Nonasymptotic Theory of Independence. Oxford University Press, Oxford

    2013

  3. [3]

    S., Paul, D., Prentice, R

    Chen, L. S., Paul, D., Prentice, R. L., and Wang, P. (2011). A regularized Hotelling's T^2 test for pathway analysis in proteomic studies. Journal of the American Statistical Association 106, 1345--1360

    2011

  4. [4]

    Chen, L., Wang, W., and Wu, W. B. (2022). Inference of breakpoints in high-dimensional time series. Journal of the American Statistical Association 117, 1951--1963

    2022

  5. [5]

    and Fryzlewicz, P

    Cho, H. and Fryzlewicz, P. (2015). Multiple-change-point detection for high dimensional time series via sparsified binary segmentation. Journal of the Royal Statistical Society: Series B 77, 475--507

    2015

  6. [6]

    and \' S niady, P

    Collins, B. and \' S niady, P. (2006). Integration with respect to the Haar measure on unitary, orthogonal and symplectic group. Communications in Mathematical Physics 264, 773--795

    2006

  7. [7]

    El Karoui, N. (2009). Concentration of measure and spectra of random matrices: Applications to correlation matrices, elliptical distributions and beyond. The Annals of Applied Probability 19, 2362--2405

    2009

  8. [8]

    and Harchaoui, Z

    Enikeeva, F. and Harchaoui, Z. (2019). High-dimensional change-point detection under sparse alternatives. The Annals of Statistics 47, 2051--2079

    2019

  9. [9]

    Fang, K.-T., Kotz, S., and Ng, K.-W. (1990). Symmetric Multivariate and Related Distributions. Chapman & Hall, London

    1990

  10. [10]

    Fryzlewicz, P. (2014). Wild binary segmentation for multiple change-point detection. The Annals of Statistics 42, 2243--2281

    2014

  11. [11]

    French, K. R. (2026). 49 industry portfolios. Kenneth R. French Data Library. https://mba.tuck.dartmouth.edu/pages/faculty/ken.french/data_library.html

    2026

  12. [12]

    James, N. A. and Matteson, D. S. (2015). ecp: An R package for nonparametric multiple change point analysis of multivariate data. Journal of Statistical Software 62, 1--25

    2015

  13. [13]

    Jiang, F., Wang, R., and Shao, X. (2023). Robust inference for change points in high dimension. Journal of Multivariate Analysis 193, 105114

    2023

  14. [14]

    Jirak, M. (2015). Uniform change point tests in high dimension. The Annals of Statistics 43, 2451--2483

    2015

  15. [15]

    and Xu, H

    Li, H. and Xu, H. (2026). Adaptable high-dimensional change point detection via ridge regularization. arXiv preprint

    2026

  16. [16]

    Li, H., Aue, A., Paul, D., Peng, J., and Wang, P. (2020). An adaptable generalization of Hotelling's T^2 test in high dimension. The Annals of Statistics 48, 1815--1847

    2020

  17. [17]

    Li, J., Chen, L., Wang, W., and Wu, W. B. (2024). _2 inference for change points in high-dimensional time series via a Two-Way MOSUM. The Annals of Statistics 52, 602--627

    2024

  18. [18]

    Lifshits, M. A. (1984). Absolute continuity of functionals of ``supremum'' type for Gaussian processes. Journal of Soviet Mathematics 27, 3103--3112

    1984

  19. [19]

    Liu, B., Zhou, C., Zhang, X., and Liu, Y. (2020). A unified data-adaptive framework for high dimensional change point detection. Journal of the Royal Statistical Society: Series B 82, 933--963

    2020

  20. [20]

    Liu, B., Zhang, X., and Liu, Y. (2022). High dimensional change point inference: Recent developments and extensions. Journal of Multivariate Analysis 188, 104833

    2022

  21. [21]

    Liu, J., Feng, L., Peng, L., and Wang, Z. (2025). Spatial-sign based high dimensional change point inference. arXiv:2504.19306

    Pith/arXiv arXiv 2025

  22. [22]

    Meckes, E. S. (2019). The Random Matrix Theory of the Classical Compact Groups. Cambridge University Press, Cambridge

    2019

  23. [23]

    Matteson, D. S. and James, N. A. (2014). A nonparametric approach for multiple change point analysis of multivariate data. Journal of the American Statistical Association 109, 334--345

    2014

  24. [24]

    O'Donnell, R. (2014). Analysis of Boolean Functions. Cambridge University Press, Cambridge

    2014

  25. [25]

    Pinelis, I. (1994). Optimum bounds for the distributions of martingales in Banach spaces. The Annals of Probability 22, 1679--1706

    1994

  26. [26]

    Shu, L., Chen, Y., Zhang, W., and Wang, X. (2022). Spatial rank-based high-dimensional change point detection via random integration. Journal of Multivariate Analysis 189, 104942

    2022

  27. [27]

    Tropp, J. A. (2012). User-friendly tail bounds for sums of random matrices. Foundations of Computational Mathematics 12, 389--434

    2012

  28. [28]

    and Feng, L

    Wang, G. and Feng, L. (2023). Computationally efficient and data-adaptive changepoint inference in high dimension. Journal of the Royal Statistical Society: Series B 85, 936--958

    2023

  29. [29]

    and Samworth, R

    Wang, T. and Samworth, R. J. (2018). High dimensional change point estimation via sparse projection. Journal of the Royal Statistical Society: Series B 80, 57--83

    2018

  30. [30]

    and Shao, X

    Wang, R. and Shao, X. (2023). Dating the break in high-dimensional data. Bernoulli 29, 2879--2901

    2023

  31. [31]

    Wang, Y., Zou, C., Wang, Z., and Yin, G. (2019). Multiple change-points detection in high dimension. Random Matrices: Theory and Applications 8, 1950014

    2019

  32. [32]

    Wang, R., Zhu, C., Volgushev, S., and Shao, X. (2022). Inference for change points in high-dimensional data via self-normalization. The Annals of Statistics 50, 781--806

    2022

  33. [33]

    Wen, M., Wang, G., Zou, C., and Wang, Z. (2024). Activation discovery with FDR control: Application to fMRI data. Statistica Sinica 34, 1625--1647

    2024

  34. [34]

    and Chen, X

    Yu, M. and Chen, X. (2021). Finite sample change point inference and identification for high-dimensional mean vectors. Journal of the Royal Statistical Society: Series B 83, 247--270

    2021

  35. [35]

    and Lavitas, L

    Zhang, T. and Lavitas, L. (2018). Unsupervised self-normalized change-point testing for time series. Journal of the American Statistical Association 113, 637--648

    2018

  36. [36]

    R., Siegmund, D

    Zhang, N. R., Siegmund, D. O., Ji, H., and Li, J. Z. (2010). Detecting simultaneous changepoints in multiple sequences. Biometrika 97, 631--645

    2010

  37. [37]

    Zhang, Y., Wang, R., and Shao, X. (2022). Adaptive inference for change points in high-dimensional data. Journal of the American Statistical Association 117, 1751--1762

    2022

  38. [38]

    Zhao, P., Zhou, L., and Feng, L. (2026). Cauchy aggregation of ridge-regularized Hotelling tests for high-dimensional change-point detection. Manuscript submitted to Random Matrices: Theory and Applications

    2026

  39. [39]

    Bai, Z. D. and Silverstein, J. W. (2010). Spectral Analysis of Large Dimensional Random Matrices, 2nd ed. Springer, New York

    2010

  40. [40]

    de Jong, P. (1987). A central limit theorem for generalized quadratic forms. Probability Theory and Related Fields 75, 261--277

    1987

  41. [41]

    Hachem, W., Loubaton, P., and Najim, J. (2007). Deterministic equivalents for certain functionals of large random matrices. The Annals of Applied Probability 17, 875--930

    2007

  42. [42]

    Hachem, W., Loubaton, P., Najim, J., and Vallet, P. (2013). On bilinear forms based on the resolvent of large random matrices. Annales de l'Institut Henri Poincare, Probabilites et Statistiques 49, 36--63

    2013

  43. [43]

    and Xu, Y

    Li, W. and Xu, Y. (2022). Asymptotic properties of high-dimensional spatial median in elliptical distributions with application. Journal of Multivariate Analysis 190, 104975

    2022

  44. [44]

    Li, W., Wang, Q., Yao, J., and Zhou, W. (2022). On eigenvalues of a high-dimensional spatial-sign covariance matrix. Bernoulli 28, 606--637

    2022

  45. [45]

    and Tyler, D

    Magyar, A. and Tyler, D. E. (2011). The asymptotic efficiency of the spatial median for elliptically symmetric distributions. Sankhya B 73, 165--192

    2011

  46. [46]

    Oja, H. (2010). Multivariate Nonparametric Methods with R: An Approach Based on Spatial Signs and Ranks. Springer, New York

    2010

  47. [47]

    Silverstein, J. W. and Choi, S. I. (1995). Analysis of the limiting spectral distribution of large-dimensional random matrices. Journal of Multivariate Analysis 54, 295--309

    1995