Pith. sign in

REVIEW 1 major objections 5 minor 295 references

For weighted data on a sphere, the paper claims the entropy deficit from uniformity can be decomposed into levelwise information gaps, with the first gap recovering vMF mean-direction information, the second isolating quadratic anisotropy,

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

2026-08-02 08:54 UTC pith:ARA7QIE6

load-bearing objection A solid, honestly scoped method paper: the GID machinery works as stated on interior moments, the boundary caveat is real but acknowledged, and it deserves a careful referee. the 1 major comments →

arxiv 2607.02943 v3 pith:ARA7QIE6 submitted 2026-07-03 stat.ME

Geometric Information Decomposition for Weighted Empirical Measures on the Sphere

Kisung You , Boram Cho This is my paper
classification stat.ME MSC 62H1162B1060D05
keywords geometric information decompositionmaximum entropyvon Mises-FisherFisher-Binghamspherical harmonicsdirectional statisticsKL divergenceweighted empirical measures
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 that a weighted point cloud on a sphere should be summarized not by a single concentration number but by a sequence of information gaps, each measuring how much entropy is removed by adding one level of harmonic features. It establishes the key identity that the cumulative entropy deficit equals the sum of KL divergences between successive maximum-entropy fits, making this profile a true decomposition into first-order, second-order, and higher-order angular information. The first gap recovers the vMF mean-direction summary, the second gap isolates antipodal, axial, elliptical, and girdle structure, and later gaps reveal finer multimodality. This matters because vMF entropy alone can badly understate uncertainty when structure is antipodal or multimodal. The paper proves invariance, consistency, normal limits away from zero gaps, and chi-square-type null calibration, and shows experimentally that the gaps separate these geometric cases.

Core claim

The central claim is that for any weighted empirical measure on a compact manifold, nested maximum-entropy projections onto feature spaces V_0 ⊂ V_1 ⊂ ⋯ give I_L(P) = D_L(P) − D_{L−1}(P) = KL(p_L ν ∥ p_{L−1}ν), so the cumulative entropy deficit D_L is exactly the sum of levelwise gaps. On the sphere, level 1 is the vMF fit, level 2 adds traceless quadratic features to capture Fisher-Bingham-type anisotropy, and levels 3 and above use spherical harmonic exponential families. The profile I_1, I_2, I_3, … therefore separates mean-direction information from axial, girdle-like, and finer angular structure that a vMF fit misses. The paper also establishes that the decomposition is invariant under

What carries the argument

The central object is the nested family of maximum-entropy (exponential-family) projections p_L that match the moments of the measure P on feature space V_L. The mechanism carrying the argument is the information-geometric Pythagorean identity for nested exponential families: the KL divergence between successive projections equals the entropy gap I_L. On the sphere, the feature spaces are the spans of spherical harmonics through degree L, with V_1 giving vMF, V_2 giving Fisher-Bingham-type quadratic structure, and higher levels giving finer angular detail. The estimable quantities are the plug-in gaps computed from weighted empirical moments, with inference relying on the moment CLT and seco

Load-bearing premise

The main load-bearing assumption is that every relevant moment vector lies in the relative interior of its convex moment body; if a weighted sample's moments sit on the boundary (e.g., equal antipodal masses, point mass, or a great-circle/girdle support), the maximum-entropy projection is degenerate or undefined, and the main results apply only after mixture shrinkage that changes the target measure.

What would settle it

Generate a large sample from a symmetric three-mode distribution on the circle (e.g., equal von Mises components at 0, 2π/3, 4π/3) and compute the Fourier gap profile with accurate quadrature. The theory predicts I_3 is the dominant gap while I_1 and I_2 are near zero. If the observed I_2 is comparable to or larger than I_3 at large n, the claimed harmonic-level separation of structure would be refuted.

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

If this is right

  • When a vMF fit is adequate, I_1 dominates and the later gaps are near zero; when structure is antipodal or girdle-like, I_2 is the large gap; when structure is trimodal or tetrahedral, the signal first appears at I_3 or higher.
  • The profile is invariant under rotation and basis changes, so it describes the geometry of the distribution rather than its coordinate representation.
  • Under the null at level L, the standardized plug-in gap converges to a weighted sum of chi-square variables; with uniform weights and correct specification, 2n Î_L converges to χ²_q, giving a formal test that the new feature level adds no information.
  • With informative weights, a naive chi-square calibration fails and a sandwich-covariance quadratic form is needed to control Type I error, as the calibration experiments demonstrate.
  • The same construction applies to any compact manifold with nested feature spaces, making the decomposition a general tool for uncertainty assessment beyond the sphere.

Where Pith is reading between the lines

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

  • Extension: because the identity holds for any compact manifold and any nested feature spaces, the same gap profile could be built on tori, projective spaces, or rotation groups, as long as interior moments and nested subspaces are available.
  • Extension: for high-dimensional embeddings where full harmonic fitting is impractical, the paper's monotonicity result implies that a structured subspace (low-rank, diagonal, or sketched quadratics) gives a lower bound on the full information gap, so the difference between structured and full gaps measures omitted information.
  • Extension: the profile offers a natural diagnostic for attention-weighted or importance-weighted representations: a dominant I_2 or I_3 indicates geometric structure that a single softmax-like direction cannot capture, which could be tested as a practical screening rule.
  • Extension: a concrete follow-up is to analyze the bias-variance tradeoff of the epsilon-mixture boundary remedy, since the paper leaves the shrinkage rate and its effect on asymptotic inference open.

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

1 major / 5 minor

Summary. The paper introduces geometric information decomposition (GID) for probability measures on the sphere, and more generally on compact Riemannian manifolds. The construction fits nested maximum-entropy exponential families to spherical harmonic and related feature spaces: level 1 recovers the von Mises-Fisher mean-direction information, level 2 captures Fisher-Bingham-type quadratic anisotropy (antipodal, axial, girdle structure), and higher levels describe finer harmonic structure. The central structural result is Theorem 1, which proves the monotonicity of entropy deficits and the KL-gap identity I_L(P)=D_L(P)-D_{L-1}(P)=KL(p_L^P nu || p_{L-1}^P nu), so that the cumulative deficit decomposes into the level-wise gaps. The paper establishes basis invariance, isometry invariance, consistency of plug-in estimators, delta-method asymptotic normality away from zero gaps, and a second-order null calibration with chi-square and weighted-chi-square limits. Simulation experiments on S^1 and S^2, including importance-weight calibration, and a query-weighted digit projection are reported. The key regularity condition is that all relevant moment vectors lie in the relative interior of the moment body.

Significance. If the stated scope is properly qualified, the paper is a solid contribution to directional statistics and information geometry. The mathematical core is sound: the proofs in Appendix C are standard and correct, the KL-gap identity follows from the nesting assumption rather than being assumed, and the delta-method and second-order null-calibration derivations check out. The experiments are carefully specified with seeds, Monte Carlo standard errors, quadrature sensitivity checks, and explicit statements about what is and is not being tested. The code is provided. The main caveat is that the GID profile is defined only when the relevant moment vectors are in the relative interior of the moment body; exact antipodal point masses, zero-thickness girdles, and other boundary configurations are outside the stated theory. This is a scope limitation rather than an internal inconsistency, and it is acknowledged in the paper, but it needs to be more prominent because the title and abstract claim a broader scope.

major comments (1)
  1. [Section 3, Assumption 4 and Section B.3] The decomposition is undefined on boundary moment vectors. The definition of p_L^P requires m_L(P) in ri(M_L), and Appendix C.1 shows the natural-parameter map is a diffeomorphism only onto the relative interior. Thus, for a weighted empirical measure supported on an exact antipodal pair or a zero-thickness girdle, the level-2 moment lies on the boundary of M_2 and no finite Fisher-Bingham projection exists; Eq. (3) and the profile are simply not defined. This is not a purely formal edge case: the antipodal and girdle examples in the Introduction are the sharp limits of exactly these boundary configurations. The remedy in B.3, mixing with the uniform measure (1-epsilon) P_w + epsilon nu, forces interiority but changes the target; the gaps then describe the shrunken measure, not P_w. The reported experiments use smooth vMF blobs and quadrature grids and therefore do not exercise the bound
minor comments (5)
  1. [Section 6.1] The sentence 'At bR=0, bkappa=0 and the direction is unidentified' could be misread as a failure of the first-level projection. For the sphere, bR=0 is actually in the interior of the moment body and the uniform vMF distribution exists; only bR=1 is a true boundary case with no finite fit. Please clarify this distinction.
  2. [Section 8.3 and Table 3] The calibration experiment tests the quadratic surrogate eI2, not the exactly fitted gap bI2. The text explicitly and honestly notes that the finite-sample remainder bI2 - eI2 is not assessed, but the section title 'Null calibration on S^2' may still mislead readers. A sentence in the table caption or section heading clarifying that only the leading quadratic term is validated would help.
  3. [Appendix A.1 and Section 7] The theory assumes exact log-partitions and optimizers, while implementation uses fixed quadrature rules. The paper correctly lists the required o_p(a_n^-1) and o_p(a_n^-2) numerical-error rates and reports sensitivity checks. Still, a short main-text remark that the inferential guarantees are asymptotic in both sample size and quadrature error would make the idealization easier for readers to track.
  4. [Theorem 8] In the displayed equation for the weighted chi-square limit, the matrix S is the Schur complement previously defined, but the notation S^{-1/2} N0 Sigma_L N0^T S^{-1/2} could be misread as using the sample covariance. A parenthetical reminder that S is the Schur complement and Sigma_L is the moment covariance would improve readability.
  5. [Header] The arXiv header lists a future version date, '29 Jul 2026'. Please ensure the final version has the correct submission/revision dates.

Circularity Check

0 steps flagged

No significant circularity; the derivation is self-contained.

full rationale

The derivation chain is self-contained. Theorem 1's KL-gap identity is proved in Appendix C.2 from nesting of feature spaces and shared moment constraints, not assumed: because p_L^P and p_{L-1}^P share all V_{L-1} moments, the proof shows KL(p_L^P nu || p_{L-1}^P nu) = D_L(P)-D_{L-1}(P). The estimation results are plug-in delta-method and second-order quadratic-form results for the population functionals D_L and I_L; no fitted constant is relabeled as a prediction. Section 6's identifications of level 1 with vMF and level 2 with Fisher-Bingham-type structure are consequences of the chosen feature spaces, not circular outputs. The main caveat, Assumption 4's interior-moment restriction, is explicit: the paper states that boundary moments can force degenerate solutions, and Appendix B.3 discloses that the shrinkage remedy changes the target measure. This is a scope limitation rather than a circular step. No load-bearing self-citation appears: the Pythagorean identity is attributed to external sources (Csiszar 1975; Amari 2001), and the authors' code repository link is not part of the argument. Accordingly, the circularity score is 0.

Axiom & Free-Parameter Ledger

3 free parameters · 6 axioms · 0 invented entities

The central derivation rests on standard exponential-family duality and the Pythagorean KL decomposition; these are legitimate axioms from prior literature. The main paper-specific assumptions are interior moments and exact integration, both stated explicitly. User choices (feature hierarchy, quadrature size, tolerances, residual cutoff) are degrees of freedom but not hidden fitted constants. No invented entities are postulated.

free parameters (3)
  • Feature hierarchy (V_0 ⊂ V_1 ⊂ ... ⊂ V_L) = User-chosen; experiments use Fourier levels 1-4 on S^1 and linear+quadratic on S^2
    The gaps are defined relative to the chosen feature spaces; changing levels or structured subspaces changes the profile. No data-driven selection rule is provided.
  • Quadrature/resolution and optimization tolerances = 4096-point grid (S^1); 30,000/50,000/80,000 Fibonacci points (S^2); BFGS dual-gradient tol 1e-6; moment-residual tol 1e-
    Theory assumes exact log-partitions and optimizers; finite rules are user-selected and their error rates for null inference are stated as requirements, not verified.
  • Residual cutoff K and weights a_l = K=8, a_l=1 in the main-text residual example
    The MMD/harmonic residual diagnostic in B.1 requires choosing K and weights; used only descriptively.
axioms (6)
  • domain assumption The feature spaces are nested finite-dimensional subspaces of L^2_0(M, ν) (Section 3)
    All identities and monotonicity rely on nesting; structured or projected features must also be nested to remain exact GID.
  • domain assumption Relevant population and empirical moments lie in the relative interior of the moment body (Assumption 4, Section 3)
    Existence of a finite max-entropy projection fails for boundary moments; bR=0 and bR=1 are explicitly acknowledged in Section 6.1; Section B.3 shrinkage changes the target measure.
  • standard math Standard regular exponential-family duality and existence theory (Brown 1986; Csiszar & Matus 2003)
    Used in Appendix C.1 to construct p_L,m and identify ri(M_L) with the natural parameter space.
  • domain assumption Moment CLT for the relevant sampling design (Eq. 5; C.10-C.11)
    Consistency and normality require a law of large numbers/CLT; for i.i.d. deterministic weights a Lindeberg condition is imposed, and for self-normalized IS finite second moment of the influence function is required.
  • ad hoc to paper Exact log-partition evaluation and optimization (Appendix A.1, Numerical inference)
    The theory assumes exact integration; a fixed quadrature rule guarantees neither o_p(a_n^-1) nor o_p(a_n^-2) numerical error. This is an idealization the paper itself flags.
  • domain assumption Correct specification and uniform weights for the exact chi-square null (Theorem 8, final statement)
    The clean chi-square limit holds only under the reduced model with equal weights; otherwise the weighted/sandwich quadratic-form calibration (8) is needed.

pith-pipeline@v1.3.0-alltime-deepseek · 15116 in / 21028 out tokens · 202739 ms · 2026-08-02T08:54:03.272885+00:00 · methodology

0 comments
read the original abstract

Weighted observations on the unit sphere arise in importance sampling, quadrature, and attention-weighted embeddings. Directional uncertainty is often summarized through a von Mises-Fisher (vMF) fit and its concentration or entropy. This summary uses only mean-direction information. It can miss antipodal, axial, girdle-like, or multimodal structure. We introduce geometric information decomposition (GID), which fits nested maximum-entropy projections to spherical features. Each gap measures the entropy reduction contributed by one feature level. The first gap is the fitted vMF distribution's KL divergence from uniformity. The second measures residual quadratic information, including Fisher-Bingham anisotropy. Later gaps describe finer angular structure. We establish invariance, consistency, alternative-regime asymptotic normality, and quadratic-form null calibration. Circular and spherical experiments include importance-weight calibration and a query-weighted digit projection. The results separate settings where vMF uncertainty is adequate from settings with higher-order structure.

Figures

Figures reproduced from arXiv: 2607.02943 by Boram Cho, Kisung You.

Figure 1
Figure 1. Figure 1: Geometry-to-information fingerprint on S 2 . The top row shows representative point clouds under an orthographic projection and the bottom row reports the first three information gaps from the harmonic maximum-entropy hierarchy. vMF structure is first-order, antipodal and girdle structure are second-order, and the tetrahedral example first appears at a higher harmonic level. level L. The increment IL(P) = … view at source ↗
Figure 2
Figure 2. Figure 2: Empirical CDFs of null-calibration p-values for the three settings in [PITH_FULL_IMAGE:figures/full_fig_p008_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Trimodal circle example. The empirical ker [PITH_FULL_IMAGE:figures/full_fig_p010_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Numerical validation of the local interpretations on [PITH_FULL_IMAGE:figures/full_fig_p011_4.png] view at source ↗

Review history (2 revisions) →

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

295 extracted references · 11 linked inside Pith

  1. [1]

    Causality:

    Pearl, Judea , year =. Causality:

  2. [2]

    and Ivanov, Sergej and Ivanov, Sergei V

    Burago, Dmitrij Jurʹevič and Burago, Jurij D. and Ivanov, Sergej and Ivanov, Sergei V. , year =. A

  3. [3]

    Methods of

    Amari, Shun'ichi and Nagaoka, Hiroshi and Amari, Shun'ichi and Amari, Shun'ichi , translator =. Methods of

  4. [4]

    Lange, Richard D and Kwok, Devin and Matelsky, Jordan Kyle and Wang, Xinyue and Rolnick, David and Kording, Konrad , editor =. Deep. Proceedings of 2nd. 2023 , pages =

    2023

  5. [5]

    Nature Communications , author =

    Single-cell analysis reveals inflammatory interactions driving macular degeneration , volume =. Nature Communications , author =. 2023 , pages =. doi:10.1038/s41467-023-37025-7 , language =

    doi:10.1038/s41467-023-37025-7 2023

  6. [6]

    The Annals of Statistics , author =

    Data-driven. The Annals of Statistics , author =. doi:10.1214/009053607000000541 , number =

    doi:10.1214/009053607000000541

  7. [7]

    , month = jan, year =

    Brown, Lawrence D. , month = jan, year =. Fundamentals of. doi:10.1214/lnms/1215466757 , urldate =

    arXiv

  8. [8]

    Transactions of the American Mathematical Society , author =

    Strong laws for \. Transactions of the American Mathematical Society , author =. 1996 , pages =. doi:10.1090/S0002-9947-96-01681-9 , language =

    doi:10.1090/s0002-9947-96-01681-9 1996

  9. [9]

    Journal of the American Statistical Association , author =

    Asymptotic. Journal of the American Statistical Association , author =. 1987 , pages =. doi:10.1080/01621459.1987.10478472 , language =

    arXiv 1987

  10. [10]

    Journal of Machine Learning Research , author =

    Scikit-learn:. Journal of Machine Learning Research , author =. 2011 , pages =

    2011

  11. [11]

    Biometrika , author =

    Saddlepoint approximations for the. Biometrika , author =. 2005 , pages =. doi:10.1093/biomet/92.2.465 , language =

    doi:10.1093/biomet/92.2.465 2005

  12. [12]

    Computational Statistics , author =

    On maximum likelihood estimation of the concentration parameter of von. Computational Statistics , author =. 2014 , pages =. doi:10.1007/s00180-013-0471-0 , language =

    doi:10.1007/s00180-013-0471-0 2014

  13. [13]

    IEEE Transactions on Information Theory , author =

    Information projections revisited , volume =. IEEE Transactions on Information Theory , author =. 2003 , pages =. doi:10.1109/TIT.2003.810633 , language =

    arXiv 2003

  14. [15]

    IEEE Transactions on Information Theory , author =

    Information geometry on hierarchy of probability distributions , volume =. IEEE Transactions on Information Theory , author =. 2001 , pages =. doi:10.1109/18.930911 , number =

    doi:10.1109/18.930911 2001

  15. [16]

    Nature Reviews Neuroscience , author =

    Neural tuning and representational geometry , volume =. Nature Reviews Neuroscience , author =. 2021 , pages =. doi:10.1038/s41583-021-00502-3 , language =

    doi:10.1038/s41583-021-00502-3 2021

  16. [17]

    New insights and perspectives on the natural gradient method , url =

    Martens, James , month = sep, year =. New insights and perspectives on the natural gradient method , url =

  17. [18]

    International Statistical Review , author =

    Directions. International Statistical Review , author =. 2022 , pages =. doi:10.1111/insr.12481 , abstract =

    doi:10.1111/insr.12481 2022

  18. [19]

    doi:10.1007/978-981-19-1044-9 , language =

    Directional. doi:10.1007/978-981-19-1044-9 , language =

    doi:10.1007/978-981-19-1044-9

  19. [20]

    On the spherical

    You, Kisung and Shung, Dennis , year =. On the spherical. doi:10.48550/ARXIV.2208.11929 , abstract =

    Pith/arXiv arXiv doi:10.48550/arxiv.2208.11929

  20. [21]

    Statistics and Computing , author =

    Learning over von. Statistics and Computing , author =. 2026 , pages =. doi:10.1007/s11222-026-10844-6 , language =

    doi:10.1007/s11222-026-10844-6 2026

  21. [22]

    Diethe, Tom , month = feb, year =. A. doi:10.48550/arXiv.1502.07104 , abstract =

    Pith/arXiv arXiv doi:10.48550/arxiv.1502.07104

  22. [23]

    doi:10.18637/jss.v058.i10 , language =

    Journal of Statistical Software , author =. doi:10.18637/jss.v058.i10 , language =

    doi:10.18637/jss.v058.i10

  23. [24]

    Communications in Statistics - Theory and Methods , author =

    A solution to the multivariate behrens-fisher problem , volume =. Communications in Statistics - Theory and Methods , author =. 1986 , pages =. doi:10.1080/03610928608829342 , language =

    doi:10.1080/03610928608829342 1986

  24. [25]

    Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences , author =

    Dispersion on a. Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences , author =. 1953 , pages =. doi:10.1098/rspa.1953.0064 , language =

    arXiv 1953

  25. [26]

    Annals of Eugenics , author =

    The. Annals of Eugenics , author =. 1936 , pages =. doi:10.1111/j.1469-1809.1936.tb02137.x , language =

    arXiv 1936

  26. [27]

    Translational Psychiatry , author =

    Brain network dysfunctions in addiction: a meta-analysis of resting-state functional connectivity , volume =. Translational Psychiatry , author =. 2022 , pages =. doi:10.1038/s41398-022-01792-6 , number =

    doi:10.1038/s41398-022-01792-6 2022

  27. [28]

    SIAM Journal on Matrix Analysis and Applications , author =

    Permutation-. SIAM Journal on Matrix Analysis and Applications , author =. 2024 , pages =. doi:10.1137/22M1538144 , language =

    doi:10.1137/22m1538144 2024

  28. [29]

    NeuroImage , author =

    Resting state functional connectivity in addiction:. NeuroImage , author =. 2012 , pages =. doi:10.1016/j.neuroimage.2012.01.117 , language =

    doi:10.1016/j.neuroimage.2012.01.117 2012

  29. [30]

    Frontiers in Human Neuroscience , author =

    Sex. Frontiers in Human Neuroscience , author =. 2019 , pages =. doi:10.3389/fnhum.2019.00104 , urldate =

    arXiv 2019

  30. [31]

    Trends in Cognitive Sciences , author =

    Functional connectomics from resting-state. Trends in Cognitive Sciences , author =. 2013 , pages =. doi:10.1016/j.tics.2013.09.016 , language =

    doi:10.1016/j.tics.2013.09.016 2013

  31. [32]

    Cerebral Cortex , author =

    Linked. Cerebral Cortex , author =. 2015 , pages =. doi:10.1093/cercor/bhu036 , language =

    doi:10.1093/cercor/bhu036 2015

  32. [33]

    ETS Research Bulletin Series , author =

    Estimating causal effects of treatments in randomized and nonrandomized studies , volume =. ETS Research Bulletin Series , author =. doi:10.1002/j.2333-8504.1972.tb00631.x , abstract =

    arXiv 1972

  33. [34]

    Biometrika , author =

    The. Biometrika , author =. 1983 , pages =. doi:10.1093/biomet/70.1.41 , language =

    doi:10.1093/biomet/70.1.41 1983

  34. [35]

    Journal of the American Statistical Association , author =

    Estimation of. Journal of the American Statistical Association , author =. 1994 , pages =. doi:10.1080/01621459.1994.10476818 , language =

    arXiv 1994

  35. [36]

    Biometrika , author =

    Quasi-oracle estimation of heterogeneous treatment effects , volume =. Biometrika , author =. 2021 , pages =. doi:10.1093/biomet/asaa076 , abstract =

    doi:10.1093/biomet/asaa076 2021

  36. [37]

    The Annals of Applied Statistics , author =

    Propensity score weighting for causal inference with multiple treatments , volume =. The Annals of Applied Statistics , author =. doi:10.1214/19-AOAS1282 , number =

    doi:10.1214/19-aoas1282

  37. [38]

    Journal of the American Statistical Association , author =

    Balancing. Journal of the American Statistical Association , author =. 2018 , pages =. doi:10.1080/01621459.2016.1260466 , language =

    arXiv 2018

  38. [39]

    Journal of the Royal Statistical Society Series B: Statistical Methodology , author =

    Causal inference on distribution functions , volume =. Journal of the Royal Statistical Society Series B: Statistical Methodology , author =. 2023 , pages =. doi:10.1093/jrsssb/qkad008 , language =

    doi:10.1093/jrsssb/qkad008 2023

  39. [40]

    Geodesic

    Kurisu, Daisuke and Zhou, Yidong and Otsu, Taisuke and Müller, Hans-Georg , year =. Geodesic. doi:10.48550/ARXIV.2406.19604 , abstract =

    Pith/arXiv arXiv doi:10.48550/arxiv.2406.19604

  40. [41]

    Proceedings of the National Academy of Sciences , author =

    Sex beyond the genitalia:. Proceedings of the National Academy of Sciences , author =. 2015 , pages =. doi:10.1073/pnas.1509654112 , abstract =

    doi:10.1073/pnas.1509654112 2015

  41. [42]

    and Robins, James M

    Hernan, Miguel A. and Robins, James M. , year =. Causal

  42. [43]

    The Econometrics Journal , author =

    Double/debiased machine learning for treatment and structural parameters , volume =. The Econometrics Journal , author =. 2018 , pages =. doi:10.1111/ectj.12097 , language =

    doi:10.1111/ectj.12097 2018

  43. [44]

    The Annals of Probability , author =

    Central limit theorems and bootstrap in high dimensions , volume =. The Annals of Probability , author =. doi:10.1214/16-AOP1113 , number =

    doi:10.1214/16-aop1113

  44. [45]

    The Annals of Statistics , author =

    Gaussian approximations and multiplier bootstrap for maxima of sums of high-dimensional random vectors , volume =. The Annals of Statistics , author =. doi:10.1214/13-AOS1161 , number =

    doi:10.1214/13-aos1161

  45. [46]

    Trends in Cognitive Sciences , author =

    Large-scale brain systems in. Trends in Cognitive Sciences , author =. 2012 , pages =. doi:10.1016/j.tics.2011.11.007 , language =

    doi:10.1016/j.tics.2011.11.007 2012

  46. [47]

    Biological Psychiatry: Cognitive Neuroscience and Neuroimaging , author =

    Intrinsic. Biological Psychiatry: Cognitive Neuroscience and Neuroimaging , author =. 2016 , pages =. doi:10.1016/j.bpsc.2016.03.004 , language =

    doi:10.1016/j.bpsc.2016.03.004 2016

  47. [48]

    Riemannian

    Collas, Antoine and Ju, Ce and Salvy, Nicolas and Thirion, Bertrand , year =. Riemannian. doi:10.48550/ARXIV.2505.18193 , abstract =

    doi:10.48550/arxiv.2505.18193

  48. [49]

    Biometrics , author =

    Doubly. Biometrics , author =. 2005 , pages =. doi:10.1111/j.1541-0420.2005.00377.x , language =

    arXiv 2005

  49. [50]

    The Annals of Statistics , author =

    Generalized random forests , volume =. The Annals of Statistics , author =. doi:10.1214/18-AOS1709 , number =

    doi:10.1214/18-aos1709

  50. [51]

    Magnetic Resonance in Medicine , author =

    Log‐. Magnetic Resonance in Medicine , author =. 2006 , pages =. doi:10.1002/mrm.20965 , abstract =

    doi:10.1002/mrm.20965 2006

  51. [52]

    1998 , keywords =

    Efficient and. 1998 , keywords =

    1998

  52. [53]

    Chwialkowski, Kacper and Strathmann, Heiko and Gretton, Arthur , editor =. A. Proceedings of. 2016 , pages =

    2016

  53. [54]

    Physical Review , author =

    On the. Physical Review , author =. 1930 , pages =. doi:10.1103/PhysRev.36.823 , language =

    doi:10.1103/physrev.36.823 1930

  54. [55]

    Orthogonal polynomials , isbn =

    Szegő, Gábor , year =. Orthogonal polynomials , isbn =

  55. [56]

    Journal of Multivariate Analysis , author =

    A new test for multivariate normality , volume =. Journal of Multivariate Analysis , author =. 2005 , pages =. doi:10.1016/j.jmva.2003.12.002 , language =

    doi:10.1016/j.jmva.2003.12.002 2005

  56. [57]

    Rayner, J. C. W. and Thas, O. and Best, D. J. , month = apr, year =. Smooth. doi:10.1002/9780470824443 , language =

    doi:10.1002/9780470824443

  57. [58]

    The Annals of Statistics , author =

    \. The Annals of Statistics , author =. doi:10.1214/aos/1176350374 , number =

    arXiv

  58. [59]

    Scandinavian Actuarial Journal , author =

    Smooth test for goodness of fit , volume =. Scandinavian Actuarial Journal , author =. 1937 , pages =. doi:10.1080/03461238.1937.10404821 , language =

    arXiv 1937

  59. [60]

    Journal für die reine und angewandte Mathematik , author =

    Ueber die. Journal für die reine und angewandte Mathematik , author =. 1866 , pages =

  60. [61]

    Biometrika , author =

    Measures of multivariate skewness and kurtosis with applications , volume =. Biometrika , author =. 1970 , pages =. doi:10.1093/biomet/57.3.519 , language =

    doi:10.1093/biomet/57.3.519 1970

  61. [62]

    Liu, Qiang and Lee, Jason and Jordan, Michael , editor =. A. Proceedings of. 2016 , pages =

    2016

  62. [63]

    Gaussian

    Janson, Svante , month = jun, year =. Gaussian. doi:10.1017/CBO9780511526169 , abstract =

    doi:10.1017/cbo9780511526169

  63. [64]

    IEEE Transactions on Neural Networks , author =

    Iterative. IEEE Transactions on Neural Networks , author =. 2011 , pages =. doi:10.1109/TNN.2011.2106511 , number =

    arXiv 2011

  64. [65]

    Journal of Machine Learning Research , author =

    Composite. Journal of Machine Learning Research , author =. 2025 , pages =

    2025

  65. [66]

    Bernoulli , author =

    A one-sample test for normality with kernel methods , volume =. Bernoulli , author =. doi:10.3150/18-BEJ1037 , number =

    doi:10.3150/18-bej1037

  66. [67]

    Communications in Statistics - Theory and Methods , author =

    A class of invariant consistent tests for multivariate normality , volume =. Communications in Statistics - Theory and Methods , author =. 1990 , pages =. doi:10.1080/03610929008830400 , language =

    doi:10.1080/03610929008830400 1990

  67. [68]

    Journal of Machine Learning Research , author =

    Spectral. Journal of Machine Learning Research , author =. 2024 , pages =

    2024

  68. [69]

    Biometrika , author =

    A test for normality based on the empirical characteristic function , volume =. Biometrika , author =. 1983 , pages =. doi:10.1093/biomet/70.3.723 , language =

    doi:10.1093/biomet/70.3.723 1983

  69. [70]

    Gaussianization , volume =

    Chen, Scott and Gopinath, Ramesh , editor =. Gaussianization , volume =. Advances in

  70. [71]

    Russian Mathematical Surveys , author =

    Ornstein–. Russian Mathematical Surveys , author =. 2018 , pages =. doi:10.1070/RM9812 , number =

    doi:10.1070/rm9812 2018

  71. [72]

    Metrika , author =

    A consistent test for multivariate normality based on the empirical characteristic function , volume =. Metrika , author =. 1988 , pages =. doi:10.1007/BF02613322 , language =

    doi:10.1007/bf02613322 1988

  72. [73]

    Journal of Machine Learning Research , author =

    On the. Journal of Machine Learning Research , author =. 2021 , pages =

    2021

  73. [74]

    Transactions of the American Mathematical Society , author =

    Theory of. Transactions of the American Mathematical Society , author =. 1950 , pages =. doi:10.1090/S0002-9947-1950-0051437-7 , language =

    doi:10.1090/s0002-9947-1950-0051437-7 1950

  74. [75]

    The Annals of Probability , author =

    Limit. The Annals of Probability , author =. doi:10.1214/aop/1176989128 , number =

    arXiv

  75. [77]

    Rosenberg, Steven , month = jan, year =. The. doi:10.1017/CBO9780511623783 , urldate =

    doi:10.1017/cbo9780511623783

  76. [78]

    Smola, Alex and Gretton, Arthur and Song, Le and Schölkopf, Bernhard , editor =. A. Algorithmic. 2007 , pages =. doi:10.1007/978-3-540-75225-7_5 , urldate =

    doi:10.1007/978-3-540-75225-7_5 2007

  77. [79]

    Signal Processing , author =

    Effective sample size for importance sampling based on discrepancy measures , volume =. Signal Processing , author =. 2017 , pages =. doi:10.1016/j.sigpro.2016.08.025 , language =

    doi:10.1016/j.sigpro.2016.08.025 2017

  78. [80]

    Ecology , author =

    Measuring diversity: the importance of species similarity , volume =. Ecology , author =. 2012 , pages =. doi:10.1890/10-2402.1 , language =

    doi:10.1890/10-2402.1 2012

  79. [81]

    Entropy , author =

    Approximation of. Entropy , author =. 2019 , pages =. doi:10.3390/e21010043 , language =

    doi:10.3390/e21010043 2019

  80. [82]

    Annales de l'Institut Henri Poincaré, Probabilités et Statistiques , author =

    The heat equation on manifolds as a gradient flow in the. Annales de l'Institut Henri Poincaré, Probabilités et Statistiques , author =. doi:10.1214/08-AIHP306 , number =

    doi:10.1214/08-aihp306

Showing first 80 references.