pith. sign in

arxiv: 2605.31579 · v1 · pith:PJYX73BNnew · submitted 2026-05-29 · 📡 eess.SP · cs.IT· math.IT· math.ST· stat.TH

Functional Multi-Target Detection via Bispectrum Inversion

Anna Little , Daniel Sanz-Alonso , Mikhail Sweeney , Ruiyi Yang This is my paper

Pith reviewed 2026-06-28 21:20 UTC · model grok-4.3

classification 📡 eess.SP cs.ITmath.ITmath.STstat.TH
keywords multi-target detectionbispectrum inversionsignal recoverycontinuous translationscorrelated Gaussian noisenon-asymptotic boundsdebiased autocorrelationcompactly supported signals
0
0 comments X

The pith

A compactly supported signal is recovered from one noisy observation containing many unknown continuous translations by estimating and inverting its bispectrum.

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

The paper establishes that signals can be recovered in a multi-target detection setting where the same compactly supported function appears at unknown continuous positions inside a single noisy record. It handles correlated stationary Gaussian noise rather than assuming white noise or grid-aligned shifts. Two algorithms first form a debiased third-order empirical autocorrelation to estimate the bispectrum, then recover the signal either by a frequency-marching procedure or by a Kotlarski-type deconvolution. Non-asymptotic error bounds are proved that depend only on the smoothness of the signal and the accuracy of the bispectrum estimate, which in turn depends on the number of signal occurrences and the noise statistics. This removes the band-limiting assumptions common in earlier discrete models.

Core claim

For compactly supported signals observed in a single record that contains many unknown continuous translations and is corrupted by correlated stationary Gaussian noise, the debiased third-order empirical autocorrelation yields a sufficiently accurate bispectrum estimate; this estimate is then inverted by either a functional frequency-marching scheme or a Kotlarski-type formula to produce a recovered signal whose error is controlled by the smoothness of the true signal and the quality of the bispectrum estimate, without any band-limiting requirement.

What carries the argument

Debiased third-order empirical autocorrelation used to estimate the bispectrum, inverted via frequency marching or Kotlarski-type deconvolution formula.

If this is right

  • Recovery guarantees hold without band-limiting the signal.
  • Error decreases as the number of signal occurrences increases or as the noise correlation structure is accounted for in the estimation step.
  • Both the frequency-marching and Kotlarski routes produce explicit non-asymptotic bounds once the bispectrum accuracy is controlled.
  • The same framework applies to low-SNR regimes once the bispectrum estimate is accurate enough.
  • The approach extends prior discrete-grid, white-noise analyses to continuous translations and correlated noise.

Where Pith is reading between the lines

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

  • The same bispectrum route could be tested on real radar or ultrasound records where target positions are truly off-grid.
  • If the bispectrum estimate remains stable under mild deviations from stationarity, the method might apply to slowly varying noise backgrounds.
  • The frequency-marching and Kotlarski routes could be compared on the same data set to see which bound is tighter for a given smoothness class.
  • The error analysis suggests that collecting more independent records would tighten the bispectrum estimate in the same way that increasing the number of occurrences does.

Load-bearing premise

The debiased third-order empirical autocorrelation must produce a sufficiently accurate bispectrum estimate despite unknown continuous translations and correlated stationary Gaussian noise.

What would settle it

A concrete counter-example or numerical trial in which the recovered-signal error exceeds the derived bound for a known smooth compactly supported signal, fixed noise variance, and known number of occurrences.

Figures

Figures reproduced from arXiv: 2605.31579 by Anna Little, Daniel Sanz-Alonso, Mikhail Sweeney, Ruiyi Yang.

Figure 1
Figure 1. Figure 1: An illustration of the MTD problem and our recovery of the signal f2 defined in (4.1). The rightmost panel is recovered via Algorithms 1 and 2 from an observation Y with noise level σ = 1, as in the center panel. Note the differing y-axes for the rightmost panel. See Section 4 for more details. algorithms are uninitialized, operate directly on the observed data, and recover the signal up to translation, wh… view at source ↗
Figure 2
Figure 2. Figure 2: Three steps in estimating the bispectrum. The left panel plots error in estimating the true number of signal occurrences as a function of the number of occurrences. The middle and right panels plot error as a function of noise intensity σ. Results are reported for all four hidden functions, with m denoting the slope of the best linear fit for each function. 4.2. Bispectrum Estimation. We first study the pe… view at source ↗
Figure 3
Figure 3. Figure 3: Error as a function of N for recovering the four hidden signals using Algorithms 1 and 2 and their ‘multi-path’ extensions. Slopes are reported for lines of best fit for each algorithm. vary from f1 to f4, the slopes of the best fit lines for all algorithms increase monotonically. This demonstrates the dependence on β for the relative error bounds in Theorem 3.7: as β increases, the relative error in recov… view at source ↗
Figure 4
Figure 4. Figure 4: c, the spectral algorithm dramatically fails; the fine spatial grid leads to very small eigenvalue gaps in the spectral decomposition of the algorithm’s bispectrum matrix, making the method highly sensitive to even minuscule noise. Thus, among uninitialized algorithms for bispectrum inversion, our proposed algorithms are better suited to the off-grid-shift setting and are more discretization-agnostic. (a) … view at source ↗
read the original abstract

This paper develops a functional theory for multi-target detection, where a compactly supported signal is recovered from a single noisy observation containing many unknown translations of the signal. Our formulation allows continuous, off-grid translations and correlated stationary Gaussian process noise, extending beyond the discrete, grid-aligned, white-noise models common in prior work. We analyze two uninitialized recovery algorithms based on autocorrelation analysis; in particular, both algorithms first estimate the signal's bispectrum via a debiased third-order empirical autocorrelation. The signal is then recovered from the estimated bispectrum using either a functional frequency marching scheme or a Kotlarski-type deconvolution formula. For both algorithms, we prove non-asymptotic recovery guarantees for compactly supported signals without bandlimiting assumptions. The resulting error bounds depend on the smoothness of the signal and the accuracy of bispectrum estimation, with the latter governed by the noise characteristics and the number of signal occurrences. Numerical experiments validate our theory and demonstrate accurate recovery in low-SNR regimes.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

1 major / 1 minor

Summary. The paper develops a functional theory for multi-target detection, recovering a compactly supported signal from one noisy observation containing many unknown continuous (off-grid) translations of the signal in correlated stationary Gaussian noise. Two uninitialized algorithms are analyzed: both estimate the bispectrum from a debiased third-order empirical autocorrelation, then invert via a functional frequency-marching scheme or a Kotlarski-type deconvolution formula. Non-asymptotic recovery guarantees are claimed for compactly supported signals without bandlimiting assumptions; the error bounds depend on signal smoothness and bispectrum estimation accuracy governed by noise and the number of occurrences.

Significance. If the guarantees hold, the work meaningfully extends discrete/grid/white-noise models to continuous translations and correlated noise, supplying non-asymptotic bounds that could support applications in radar or imaging. The explicit dependence of rates on smoothness and bispectrum accuracy, together with the two inversion routes, is a positive feature.

major comments (1)
  1. [Abstract] Abstract: the non-asymptotic recovery guarantees rest on the debiased third-order empirical autocorrelation converging to the true bispectrum at a rate sufficient for the subsequent inversion. No explicit control is given on the remainder arising from the mismatch between the continuous unknown shift distribution and the finite-sample empirical measure, nor on propagation of covariance-estimation error (required for debiasing under correlated stationary Gaussian noise) into the bispectrum. This step is load-bearing for the claimed error bounds.
minor comments (1)
  1. The abstract mentions numerical experiments validating the theory but does not indicate the range of SNR or number of occurrences tested; adding this would help readers assess the practical regime.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for the careful reading and positive assessment of the work's potential significance in extending multi-target detection theory. We address the single major comment below.

read point-by-point responses

  1. Referee: [Abstract] Abstract: the non-asymptotic recovery guarantees rest on the debiased third-order empirical autocorrelation converging to the true bispectrum at a rate sufficient for the subsequent inversion. No explicit control is given on the remainder arising from the mismatch between the continuous unknown shift distribution and the finite-sample empirical measure, nor on propagation of covariance-estimation error (required for debiasing under correlated stationary Gaussian noise) into the bispectrum. This step is load-bearing for the claimed error bounds.

    Authors: We agree that explicit control on these terms is essential for the claimed non-asymptotic bounds and that the abstract does not reference them. The full analysis (Theorem 3.1 and its proof, supported by Lemma 4.2 on empirical-process concentration for the unknown shift distribution and Proposition 5.3 on covariance estimation under stationary Gaussian noise) does bound both the empirical-measure mismatch remainder and the propagation of covariance error into the bispectrum estimator via Lipschitz continuity of the third-order moment functional. However, these controls are not highlighted in the abstract or theorem statement. We will revise the abstract to note the dependence on bispectrum estimation accuracy (including these terms) and add a short clarifying remark after Theorem 3.1. This is a presentation improvement rather than a change to the underlying analysis. revision: yes

Circularity Check

0 steps flagged

No significant circularity; derivation relies on standard bispectrum properties

full rationale

The paper's central claims consist of non-asymptotic recovery bounds for two inversion algorithms (frequency marching and Kotlarski-type) that take a debiased third-order autocorrelation estimate as input and produce signal recovery error controlled by bispectrum accuracy plus signal smoothness. These bounds are derived from the estimation error of the bispectrum under the stated noise and translation model; the estimation step itself is not shown to reduce to a fitted parameter or self-referential definition. No load-bearing self-citations, uniqueness theorems imported from the authors' prior work, or ansatzes smuggled via citation appear in the abstract or derivation outline. The approach is self-contained against external benchmarks of bispectrum inversion theory.

Axiom & Free-Parameter Ledger

0 free parameters · 2 axioms · 0 invented entities

Based solely on the abstract; full paper may contain additional assumptions. No free parameters or invented entities are mentioned. Relies on standard properties of bispectrum and autocorrelation.

axioms (2)
  • domain assumption The observed signal consists of multiple unknown translations of a compactly supported function plus correlated stationary Gaussian noise
    Stated as the problem setup enabling the bispectrum approach.
  • domain assumption The third-order empirical autocorrelation can be debiased to yield a consistent bispectrum estimate
    Central to both recovery algorithms described in the abstract.

pith-pipeline@v0.9.1-grok · 5706 in / 1238 out tokens · 26593 ms · 2026-06-28T21:20:04.054339+00:00 · methodology

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

60 extracted references · 1 linked inside Pith

  1. [1]

    A. Abas, T. Bendory, and N. Sharon , The generalized method of moments for multi-reference alignment , IEEE Transactions on Signal Processing, 70 (2022), pp. 1377--1388

    2022

  2. [2]

    E. Abbe, T. Bendory, W. Leeb, J. M. Pereira, N. Sharon, and A. Singer , Multireference alignment is easier with an aperiodic translation distribution , IEEE Transactions on Information Theory, 65 (2018), pp. 3565--3584

    2018

  3. [3]

    Abraham, A

    K. Abraham, A. Balanov, T. Bendory, and C. Esteve-Yag \"u e , Sample complexity analysis of multi-target detection via Markovian and hard-core multi-reference alignment , arXiv preprint arXiv:2510.17775, (2025)

    arXiv 2025

  4. [4]

    Aguerrebere, M

    C. Aguerrebere, M. Delbracio, A. Bartesaghi, and G. Sapiro , Fundamental limits in multi-image alignment , 02 2016

    2016

  5. [5]

    Al-Ghattas, A

    O. Al-Ghattas, A. Little, D. Sanz-Alonso, and M. Sweeney , Functional multi-reference alignment via deconvolution , SIAM Journal on Mathematics of Data Science, (2025). To appear

    2025

  6. [6]

    Balanov, T

    A. Balanov, T. Bendory, and D. Edidin , Orbit recovery under the rigid motions group , arXiv preprint arXiv:2512.07405, (2025)

    arXiv 2025

  7. [7]

    height 2pt depth -1.6pt width 23pt, Group-invariant moments under tomographic projections , arXiv preprint arXiv:2604.08330, (2026)

    Pith/arXiv arXiv 2026

  8. [8]

    Balanov, W

    A. Balanov, W. Huleihel, and T. Bendory , Expectation-maximization for multi-reference alignment: Two pitfalls and one remedy , arXiv preprint arXiv:2505.21435, (2025)

    arXiv 2025

  9. [9]

    height 2pt depth -1.6pt width 23pt, Einstein from noise: Statistical analysis , IEEE Transactions on Signal Processing, (2026)

    2026

  10. [10]

    Balanov, S

    A. Balanov, S. Kreymer, and T. Bendory , A note on the sample complexity of multi-target detection , in 2025 International Conference on Sampling Theory and Applications (SampTA), IEEE, 2025, pp. 1--5

    2025

  11. [11]

    Bandeira, Y

    A. Bandeira, Y. Chen, R. R. Lederman, and A. Singer , Non-unique games over compact groups and orientation estimation in cryo-EM , Inverse Problems, (2020)

    2020

  12. [12]

    V. R. Bejjanki, R. A. Da Silveira, J. D. Cohen, and N. B. Turk-Browne , Noise correlations in the human brain and their impact on pattern classification , PLoS Computational Biology, 13 (2017), p. e1005674

    2017

  13. [13]

    Bendory, N

    T. Bendory, N. Boumal, W. Leeb, E. Levin, and A. Singer , Multi-target detection with application to cryo-electron microscopy , Inverse Problems, 35 (2019), p. 104003

    2019

  14. [14]

    886--910

    height 2pt depth -1.6pt width 23pt, Toward single particle reconstruction without particle picking: Breaking the detection limit , SIAM Journal on Imaging Sciences, 16 (2023), pp. 886--910

    2023

  15. [15]

    Bendory, N

    T. Bendory, N. Boumal, C. Ma, Z. Zhao, and A. Singer , Bispectrum inversion with application to multireference alignment , IEEE Transactions on Signal Processing, 66 (2017), pp. 1037--1050

    2017

  16. [16]

    1037–1050

    height 2pt depth -1.6pt width 23pt, Bispectrum inversion with application to multireference alignment , IEEE Transactions on Signal Processing, 66 (2018), p. 1037–1050

    2018

  17. [17]

    Bendory, D

    T. Bendory, D. Edidin, J. Katz, S. Kreymer, and N. Sharon , Provable orbit recovery over so(3) from the non-uniform second moment , arXiv preprint arXiv:2602.20590, (2026)

    arXiv 2026

  18. [18]

    Bendory, T.-Y

    T. Bendory, T.-Y. Lan, N. Marshall, I. Rukshin, and A. Singer , Multi-target detection with rotations , Inverse Problems and Imaging, 17 (2022)

    2022

  19. [19]

    Bepler, K

    T. Bepler, K. Kelley, A. Noble, and B. Berger , Topaz-denoise: general deep denoising models for cryoem and cryoet , Nature Communications, 11 (2020)

    2020

  20. [20]

    T. A. M. Bharat and S. H. W. Scheres , Resolving macromolecular structures from electron cryo-tomography data using subtomogram averaging in RELION , Nature Protocols, 11 (2016), pp. 2054--2065

    2016

  21. [21]

    C. J. Cameron, S. J. Seager, F. J. Sigworth, H. D. Tagare, and M. B. Gerstein , REliable PIcking by Consensus (REPIC): a consensus methodology for harnessing multiple cryo-EM particle pickers , Communications Biology, 7 (2024), p. 1421

    2024

  22. [22]

    H. Chen, M. Zehni, and Z. Zhao , A spectral method for stable bispectrum inversion with application to multireference alignment , IEEE Signal Processing Letters, 25 (2018), p. 911–915

    2018

  23. [23]

    Collis, P

    W. Collis, P. White, and J. Hammond , Higher-order spectra: the bispectrum and trispectrum , Mechanical Systems and Signal Processing, 12 (1998), pp. 375--394

    1998

  24. [24]

    Comte and J

    F. Comte and J. Kappus , Density deconvolution from repeated measurements without symmetry assumption on the errors , Journal of Multivariate Analysis, 140 (2015), pp. 31--46

    2015

  25. [25]

    A. P. Dempster, N. M. Laird, and D. B. Rubin , Maximum likelihood from incomplete data via the EM algorithm , Journal of the Royal Statistical Society: Series B (Methodological), 39 (1977), pp. 1--22

    1977

  26. [26]

    Z. Dou, Z. Fan, and H. H. Zhou , Rates of estimation for high-dimensional multireference alignment , The Annals of Statistics, 52 (2024), pp. 261--284

    2024

  27. [27]

    Drozatz, T

    G. Drozatz, T. Bendory, and N. Sharon , Provable algorithms for multi-reference alignment over SO (2) , in 2025 33rd European Signal Processing Conference (EUSIPCO), IEEE, 2025, pp. 2762--2766

    2025

  28. [28]

    Foucart and H

    S. Foucart and H. Rauhut , A Mathematical Introduction to Compressive Sensing , Springer Birkh\" a user, 2013

    2013

  29. [29]

    Glaeser , Review: Electron crystallography: Present excitement, a nod to the past, anticipating the future , Journal of structural biology, 128 (2000), pp

    R. Glaeser , Review: Electron crystallography: Present excitement, a nod to the past, anticipating the future , Journal of structural biology, 128 (2000), pp. 3--14

    2000

  30. [30]

    Gogineni, P

    S. Gogineni, P. Setlur, M. Rangaswamy, and R. R. Nadakuditi , Passive radar detection with noisy reference channel using principal subspace similarity , IEEE Transactions on Aerospace and Electronic Systems, 54 (2018), pp. 18--36

    2018

  31. [31]

    L. P. Hansen , Large sample properties of generalized method of moments estimators , Econometrica: Journal of the Econometric Society, (1982), pp. 1029--1054

    1982

  32. [32]

    Hazon, V

    O. Hazon, V. H. Minces, D. P. Tom \`a s, S. Ganguli, M. J. Schnitzer, and P. E. Jercog , Noise correlations in neural ensemble activity limit the accuracy of hippocampal spatial representations , Nature Communications, 13 (2022), p. 4276

    2022

  33. [33]

    Henderson , Avoiding the pitfalls of single particle cryo-electron microscopy: Einstein from noise , Proceedings of the National Academy of Sciences, 110 (2013), pp

    R. Henderson , Avoiding the pitfalls of single particle cryo-electron microscopy: Einstein from noise , Proceedings of the National Academy of Sciences, 110 (2013), pp. 18037--18041

    2013

  34. [34]

    Hirn and A

    M. Hirn and A. Little , Wavelet invariants for statistically robust multi-reference alignment , Information and Inference: A Journal of the IMA, 10 (2021), pp. 1287--1351

    2021

  35. [35]

    height 2pt depth -1.6pt width 23pt, Power spectrum unbiasing for dilation-invariant multi-reference alignment , Journal of Fourier Analysis and Applications, 29 (2023), p. 43

    2023

  36. [36]

    Huang and S

    X. Huang and S. G. Lisberger , Noise correlations in cortical area mt and their potential impact on trial-by-trial variation in the direction and speed of smooth-pursuit eye movements , Journal of Neurophysiology, 101 (2009), pp. 3012--3030

    2009

  37. [37]

    Kallenberg , Foundations of modern probability , Springer, 1997

    O. Kallenberg , Foundations of modern probability , Springer, 1997

    1997

  38. [38]

    Kam , The reconstruction of structure from electron micrographs of randomly oriented particles , in Electron Microscopy at Molecular Dimensions, Springer, 1980, pp

    Z. Kam , The reconstruction of structure from electron micrographs of randomly oriented particles , in Electron Microscopy at Molecular Dimensions, Springer, 1980, pp. 270--277

    1980

  39. [39]

    Kam , The reconstruction of structure from electron micrographs of randomly oriented particles , Journal of Theoretical Biology, 82 (1980), pp

    Z. Kam , The reconstruction of structure from electron micrographs of randomly oriented particles , Journal of Theoretical Biology, 82 (1980), pp. 15--39

    1980

  40. [40]

    Kotlarski , On characterizing the gamma and the normal distribution , Pacific Journal of Mathematics, 20 (1967), pp

    I. Kotlarski , On characterizing the gamma and the normal distribution , Pacific Journal of Mathematics, 20 (1967), pp. 69--76

    1967

  41. [41]

    Kreymer and T

    S. Kreymer and T. Bendory , Two-dimensional multi-target detection: An autocorrelation analysis approach , IEEE Transactions on Signal Processing, 70 (2022), p. 835–849

    2022

  42. [42]

    Kreymer, A

    S. Kreymer, A. Singer, and T. Bendory , An approximate expectation-maximization for two-dimensional multi-target detection , IEEE Signal Processing Letters, 29 (2022), pp. 1087--1091

    2022

  43. [43]

    Kreymer, A

    S. Kreymer, A. Singer, and T. Bendory , Expectation-maximization for structure determination directly from cryo-EM micrographs , arXiv:2303.02157, (2026)

    arXiv 2026

  44. [44]

    Kurisu and T

    D. Kurisu and T. Otsu , On the uniform convergence of deconvolution estimators from repeated measurements , Econometric Theory, 38 (2022), pp. 172--193

    2022

  45. [45]

    T.-Y. Lan, T. Bendory, N. Boumal, and A. Singer , Multi-target detection with an arbitrary spacing distribution , IEEE Transactions on Signal Processing, 68 (2020), pp. 1589--1601

    2020

  46. [46]

    M. S. Lewicki , A review of methods for spike sorting: the detection and classification of neural action potentials , Network: Computation in Neural Systems, 9 (1998), pp. R53--R78

    1998

  47. [47]

    Li and Q

    T. Li and Q. Vuong , Nonparametric estimation of the measurement error model using multiple indicators , Journal of Multivariate Analysis, 65 (1998), pp. 139--165

    1998

  48. [48]

    Major , , in Multiple Wiener-It \^o Integrals: With Applications to Limit Theorems, Springer, 2006, pp

    P. Major , , in Multiple Wiener-It \^o Integrals: With Applications to Limit Theorems, Springer, 2006, pp. 22--37

    2006

  49. [49]

    N. F. Marshall, T.-Y. Lan, T. Bendory, and A. Singer , Image recovery from rotational and translational invariants , in ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE, May 2020, p. 5780–5784

    2020

  50. [50]

    Meister , Deconvolution Problems in Nonparametric Statistics , vol

    A. Meister , Deconvolution Problems in Nonparametric Statistics , vol. 193, Lecture Notes in Statistics. Springer-Verlag, 2007

    2007

  51. [51]

    Nualart , The Malliavin Calculus and Related Topics , Springer, 2006

    D. Nualart , The Malliavin Calculus and Related Topics , Springer, 2006

    2006

  52. [52]

    Perry, J

    A. Perry, J. Weed, A. S. Bandeira, P. Rigollet, and A. Singer , The sample complexity of multireference alignment , SIAM Journal on Mathematics of Data Science, 1 (2019), pp. 497--517

    2019

  53. [53]

    B. L. S. P. Rao , Identifiability in Stochastic Models , Academic Press, 1992

    1992

  54. [54]

    B. M. Sadler and G. B. Giannakis , Shift- and rotation-invariant object reconstruction using the bispectrum , J. Opt. Soc. Am. A, 9 (1992), pp. 57--69

    1992

  55. [55]

    Shalit, R

    Y. Shalit, R. Weber, A. Abas, S. Kreymer, and T. Bendory , Generalized autocorrelation analysis for multi-target detection , in ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE, May 2022, p. 5907–5911

    2022

  56. [56]

    Sharon, J

    N. Sharon, J. Kileel, Y. Khoo, B. Landa, and A. Singer , Method of moments for 3-D single particle ab initio modeling with non-uniform distribution of viewing angles , Inverse Problems, 36 (2020), p. 044003

    2020

  57. [57]

    F. G. Viens and A. B. Vizcarra , Supremum concentration inequality and modulus of continuity for sub-nth chaos processes , Journal of Functional Analysis, 248 (2007), pp. 1--26

    2007

  58. [58]

    N. Voss, C. Yoshioka, M. Radermacher, C. Potter, and B. Carragher , Dog picker and tiltpicker: Software tools to facilitate particle selection in single particle electron microscopy , Journal of structural biology, 166 (2009), pp. 205--13

    2009

  59. [59]

    Wendland , Scattered Data Approximation , Cambridge Monographs on Applied and Computational Mathematics, Cambridge University Press, 2004

    H. Wendland , Scattered Data Approximation , Cambridge Monographs on Applied and Computational Mathematics, Cambridge University Press, 2004

    2004

  60. [60]

    Zabatani, S

    A. Zabatani, S. Kreymer, and T. Bendory , Score-based diffusion priors for multi-target detection , arXiv:2312.08500, (2023)

    arXiv 2023