pith. sign in

arxiv: 2606.30958 · v1 · pith:ZECPVPAAnew · submitted 2026-06-29 · 📊 stat.ME · math.OC· math.ST· stat.ML· stat.TH

Exponential-Family Tensor Completion via Nonconvex Dual Total-Variation Regularization

Wenfei Cao , Yang Chen , Qibin Zhao , Jinglai Li , Andrzej Cichocki This is my paper

Pith reviewed 2026-07-01 01:11 UTC · model grok-4.3

classification 📊 stat.ME math.OCmath.STstat.MLstat.TH
keywords tensor completiondual total variationexponential familynonconvex regularizationrecovery error boundsminimax analysisgradient sparsitylow-rank structure
0
0 comments X

The pith

Dual total-variation regularizers based on transformed L1 yield recovery error bounds for exponential-family tensor completion that approach the minimax lower bound.

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

The paper develops regularization for recovering tensors from partial observations under exponential-family noise, which includes Gaussian and Poisson cases. It introduces a family of dual-TV regularizers that enforce both sparsity and low-rank structure on the gradient tensor. Theoretical analysis derives upper bounds on the estimator's recovery error that reach order O(n3 rt (max sk^2) log((n1+n2)n3)/n) in some regimes. Minimax lower-bound analysis shows these upper bounds are within a gap of order O(max sk^2 / max(n1,n2)) up to a logarithmic factor. Experiments on synthetic, image, and video data illustrate the approach.

Core claim

We propose a family of dual-TV regularizers based on the transformed L1 function for exponential-family tensor completion. These regularizers simultaneously capture sparsity and low-rank structures in the gradient tensor. We establish upper bounds on the recovery error that can attain the order O(n3 rt (maxk sk^2) log((n1+n2)n3)/n), and show via minimax analysis that these bounds approach the lower bound with a gap of O(maxk sk^2 / max(n1,n2)) up to a logarithmic factor.

What carries the argument

The family of dual-TV (DTV) regularizers based on the transformed L1 function, which simultaneously enforce sparsity and low-rank structure on the gradient tensor of the target.

If this is right

  • Recovery error is bounded by O(n3 rt (max sk^2) log((n1+n2)n3)/n) under the modeling assumptions.
  • The estimator approaches minimax optimality because the upper bound is within O(max sk^2 / max(n1,n2)) of the lower bound up to logs.
  • The framework covers general exponential-family noise, recovering Gaussian and Poisson tensor completion as special cases.
  • The regularizer is nonconvex and handles both synthetic and real tensor data such as images and videos.

Where Pith is reading between the lines

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

  • The same regularizer structure might be tested on other inverse problems where data gradients are expected to be sparse and low-rank.
  • If the simultaneous sparsity-low-rank assumption is weakened, the error rates could still hold under milder conditions on the gradient.
  • The derived rates suggest that computational implementations could be scaled to larger tensors while preserving the theoretical guarantees.

Load-bearing premise

The gradient tensor of the target admits simultaneous sparsity and low-rank structure that the specific transformed-L1 dual-TV regularizer can capture.

What would settle it

A concrete counter-example would be an instance where the gradient tensor satisfies the sparsity and low-rank conditions yet the observed recovery error exceeds the stated upper bound by more than the predicted gap of order O(max sk^2 / max(n1,n2)).

Figures

Figures reproduced from arXiv: 2606.30958 by Andrzej Cichocki, Jinglai Li, Qibin Zhao, Wenfei Cao, Yang Chen.

Figure 1
Figure 1. Figure 1: Boxplots of (a) MPSNR and (b) MSSIM over 20 videos for Gaussian tensor completion with a sampling ratio of 0.2. [PITH_FULL_IMAGE:figures/full_fig_p003_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Illustration of the simultaneous low-rankness and sparsity of the gradient tensor (see Definition [PITH_FULL_IMAGE:figures/full_fig_p007_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Convergence of Algorithm 1 for three types of noise. -2 -1 0 1 2 3 log10(a) 1.2 1.4 1.6 1.8 2 2.2 2.4 2.6 MSE 10-4 (a) Gaussian Tensor Completion -2 -1 0 1 2 3 log10(a) 3.5 4 4.5 5 5.5 6 6.5 7 7.5 8 8.5 MSE (b) Poisson Tensor Completion (c) One-bit Tensor Completion [PITH_FULL_IMAGE:figures/full_fig_p015_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Sensitivity analysis for the internal parameters ( [PITH_FULL_IMAGE:figures/full_fig_p015_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Recovery performance for three kinds of tensor completion with TCTV regularization and TDTV [PITH_FULL_IMAGE:figures/full_fig_p015_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Visual comparison for the videos ‘highway’ (frame [PITH_FULL_IMAGE:figures/full_fig_p018_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: Sensitivity analysis of regularization parameters [PITH_FULL_IMAGE:figures/full_fig_p019_7.png] view at source ↗
read the original abstract

With the emergence of various tensor data, tensor completion from partial measurements has attracted widespread attention in data science and signal processing. Total Variation (TV) has been widely used as an effective regularization technique for tensor completion; however, theoretical studies on TV regularization in this context remain limited. In this work, we present a rigorous theoretical analysis of TV regularization for tensor completion. Specifically, we consider tensor completion under exponential-family noise, which generalizes the standard settings such as Gaussian and Poisson tensor completion. To handle exponential-family tensor completion, we propose a family of dual-TV (DTV) regularizers based on the transformed L1 function, which simultaneously capture sparsity and low-rank structures in the gradient tensor. Moreover, we establish the theoretical upper bounds on the recovery error of the proposed estimator. In certain cases, these upper bounds can attain the convergence order of $\mathcal{O}\big( n_3 r_t\big(\max_{k} s_k^2\big) \log\big((n_1+n_2)n_3\big) /n \big)$, and the minimax lower bound analysis is further presented to show that the upper-bounds can approach the lower bound with the gap of order $\mathcal{O}(\max_k s_k^2/max(n_1, n_2))$ up to a logarithmic factor. Finally, multiple groups of experiments on synthetic, image and video tensor data sets are conducted to support our theoretical results and demonstrate the effectiveness of our method.

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

3 major / 2 minor

Summary. The manuscript proposes a family of nonconvex dual total-variation (DTV) regularizers based on the transformed L1 function for tensor completion under exponential-family noise. It claims to derive upper bounds on the recovery error of the proposed estimator that attain the rate O(n_3 r_t (max_k s_k^2) log((n1+n2)n3)/n) in certain cases, and presents minimax lower-bound analysis showing that the upper bounds approach optimality with a gap of order O(max_k s_k^2 / max(n1,n2)) up to logarithmic factors. Experiments on synthetic, image, and video tensors are included to support the claims.

Significance. If the stated bounds hold under the paper's modeling assumptions, the work would provide a useful theoretical contribution to tensor completion by extending TV regularization to general exponential-family noise while jointly capturing sparsity and low-rank structure in the gradient tensor. The near-matching of upper and lower bounds would be a positive feature, and the experimental results on real data would add practical support.

major comments (3)
  1. [Abstract] Abstract and theoretical sections: the manuscript asserts rigorous derivation of the upper bound O(n_3 r_t (max_k s_k^2) log((n1+n2)n3)/n) and the minimax lower-bound gap, yet supplies no derivation steps, no explicit assumption list, and no verification that the transformed-L1 DTV construction produces the claimed rates under the exponential-family likelihood; these steps are load-bearing for the central theoretical contribution.
  2. [Modeling section on DTV regularizers] Modeling section on DTV regularizers: the claim that the gradient tensor admits simultaneous sparsity and low-rank structure exactly captured by the transformed-L1 family is invoked to obtain the error bounds, but the manuscript does not demonstrate necessity or sufficiency of this structure nor verify that the regularizer enforces it under the given noise model.
  3. [Theoretical analysis] Theoretical analysis: the upper and lower bounds are presented as following from the estimator definition, but without shown intermediate steps it is impossible to confirm whether the rates reduce to quantities defined solely by the fitted parameters or require additional unstated conditions on the gradient tensor.
minor comments (2)
  1. [Notation] Notation for dimensions (n, n1, n2, n3) and parameters (r_t, s_k) should be defined once at first use and used consistently.
  2. [Abstract] The phrase 'in certain cases' for the upper-bound rate should be replaced by an explicit statement of the conditions under which the rate holds.

Simulated Author's Rebuttal

3 responses · 0 unresolved

We thank the referee for the careful reading and constructive comments. We address each major comment below and will revise the manuscript accordingly to improve clarity of the theoretical contributions.

read point-by-point responses

  1. Referee: [Abstract] Abstract and theoretical sections: the manuscript asserts rigorous derivation of the upper bound O(n_3 r_t (max_k s_k^2) log((n1+n2)n3)/n) and the minimax lower-bound gap, yet supplies no derivation steps, no explicit assumption list, and no verification that the transformed-L1 DTV construction produces the claimed rates under the exponential-family likelihood; these steps are load-bearing for the central theoretical contribution.

    Authors: We agree that the main text presents the bounds without full intermediate derivation steps. The complete proofs appear in the appendix, but to address this we will add an explicit assumption list and a high-level proof sketch in the main theoretical section of the revision, showing how the transformed-L1 DTV yields the stated rates under the exponential-family likelihood. revision: yes

  2. Referee: [Modeling section on DTV regularizers] Modeling section on DTV regularizers: the claim that the gradient tensor admits simultaneous sparsity and low-rank structure exactly captured by the transformed-L1 family is invoked to obtain the error bounds, but the manuscript does not demonstrate necessity or sufficiency of this structure nor verify that the regularizer enforces it under the given noise model.

    Authors: The modeling choice is motivated by the observation that gradient tensors of image and video data commonly exhibit joint sparsity and low-rank structure. The transformed-L1 family is selected as a nonconvex surrogate that promotes both. We will expand the modeling section in revision to include a discussion of sufficiency for the error bounds and interaction with the exponential-family noise model. revision: yes

  3. Referee: [Theoretical analysis] Theoretical analysis: the upper and lower bounds are presented as following from the estimator definition, but without shown intermediate steps it is impossible to confirm whether the rates reduce to quantities defined solely by the fitted parameters or require additional unstated conditions on the gradient tensor.

    Authors: The bounds rely on the structural assumptions (sparsity and low-rankness) of the gradient tensor that are captured by the regularizer. We will include the key intermediate steps and clarify in the revised theoretical analysis which quantities depend only on fitted parameters versus the gradient-tensor assumptions. revision: yes

Circularity Check

0 steps flagged

No circularity: error bounds derived conditionally from explicit structural assumptions on the gradient tensor.

full rationale

The paper states theoretical upper bounds on recovery error for the proposed estimator under the modeling assumption that the gradient tensor admits simultaneous sparsity and low-rank structure captured by the transformed-L1 dual-TV regularizers, with the bounds attaining the stated rate 'in certain cases' and approaching the minimax lower bound up to the noted gap. This constitutes standard conditional analysis in statistical estimation theory rather than any self-definitional reduction, fitted-input prediction, or self-citation load-bearing step; the rates do not reduce by construction to quantities defined via the same fitted parameters, and no load-bearing self-citations or ansatzes are invoked in the abstract or described claims. The derivation chain is therefore self-contained against external benchmarks.

Axiom & Free-Parameter Ledger

0 free parameters · 2 axioms · 0 invented entities

Abstract-only review; the central claim rests on unstated modeling assumptions about the gradient tensor structure and the validity of the transformed-L1 dual-TV family for capturing both sparsity and low-rank, plus standard exponential-family likelihood assumptions. No free parameters or invented entities are explicitly introduced in the abstract.

axioms (2)
  • domain assumption The observed tensor entries follow an exponential-family distribution with the true tensor as natural parameter.
    Invoked to generalize beyond Gaussian/Poisson settings (abstract opening).
  • domain assumption The gradient tensor admits a structure simultaneously sparse and low-rank that the dual-TV regularizer can exploit.
    Required for the stated error bounds to hold (abstract paragraph on DTV regularizers).

pith-pipeline@v0.9.1-grok · 5817 in / 1448 out tokens · 35147 ms · 2026-07-01T01:11:41.165598+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 · 60 canonical work pages

  1. [1]

    Multilayer tensor factorization with applications to recommender systems,

    X. Bi, A. Qu, and X. Shen, “Multilayer tensor factorization with applications to recommender systems,”Ann. of Statist., vol. 46, no. 6B, pp. 3308–3333, 2018

    work page 2018

  2. [2]

    A three-way model for collective learning on multi-relational data,

    M. Nickel, V . Tresp, and H. P. Kriegel, “A three-way model for collective learning on multi-relational data,”Int. Conf. Machine Learning, vol. 11, pp. 809–816, 2011

    work page 2011

  3. [3]

    Tensors for data mining and data fusion: Models, applications, and scalable algorithms,

    E. E. Papalexakis, C. Faloutsos, and N. D. Sidiropoulos, “Tensors for data mining and data fusion: Models, applications, and scalable algorithms,” ACM Trans. Intell. Syst. Technol., vol. 8, no. 2, pp. 1–44, 2016. [Online]. Available: https://doi.org/10.1145/2915921

    work page doi:10.1145/2915921 2016

  4. [4]

    Tensor decompositions and applications,

    T. G. Kolda and B. W. Bader, “Tensor decompositions and applications,”SIAM Rev., vol. 51, no. 3, pp. 455–500, 2009

    work page 2009

  5. [5]

    Tensor networks for dimensionality reduction and large-scale optimization: Part 1 low-rank tensor decompositions,

    A. Cichocki, N. Lee, I. Oseledets, A.-H. Phan, Q. Zhao, and D. P. Mandic, “Tensor networks for dimensionality reduction and large-scale optimization: Part 1 low-rank tensor decompositions,”Found. Trends Mach. Learn., vol. 9, no. 4–5, p. 249–429, 2016

    work page 2016

  6. [6]

    Tensor methods in computer vision and deep learning,

    Y . Panagakis, J. Kossaifi, S. Clara, G. G. Chrysos, J. Oldfield, M. A. Nicolaou, A. Anandkumar, and S. Zafeiriou, “Tensor methods in computer vision and deep learning,”Proceedings of the IEEE, vol. 109, no. 5, pp. 863–890, 2021

    work page 2021

  7. [7]

    Tensor completion algorithms in big data analytics,

    Q. Song, H. Ge, J. Caverlee, and X. Hu, “Tensor completion algorithms in big data analytics,”ACM Trans. Knowl. Discov. Data, vol. 13, no. 6, pp. 1–48, 2019

    work page 2019

  8. [8]

    Nonlinear total variation based noise removal algorithms,

    L. I. Rudin, S. Osher, and E. Fatemi, “Nonlinear total variation based noise removal algorithms,”Physica D: nonlinear phenomena, vol. 60, no. 1-4, pp. 259–268, 1992

    work page 1992

  9. [9]

    Total variation inpainting using split bregman,

    P. Getreuer, “Total variation inpainting using split bregman,”Image Processing On Line, vol. 2, pp. 147–157, 2012

    work page 2012

  10. [10]

    An introduction to continuous optimization for imaging,

    A. Chambolle and T. Pock, “An introduction to continuous optimization for imaging,”Acta Numerica, vol. 25, pp. 161–319, 2016

    work page 2016

  11. [11]

    Approximation theory of total variation minimization for data completion,

    J.-F. Cai, J. K. Choi, and K. Wei, “Approximation theory of total variation minimization for data completion,”arXiv preprint arXiv:2207.07473, 2022

    work page arXiv 2022

  12. [12]

    Low-rank tensor completion with total variation for visual data inpainting,

    X. Li, Y . Ye, and X. Xu, “Low-rank tensor completion with total variation for visual data inpainting,” inProceedings of the AAAI Conference on Artificial Intelligence, vol. 31, no. 1, 2017

    work page 2017

  13. [13]

    Robust low-rank tensor completion via transformed tensor nuclear norm with total variation regularization,

    D. Qiu, M. Bai, M. K. P. Ng, and X. Zhang, “Robust low-rank tensor completion via transformed tensor nuclear norm with total variation regularization,” Neurocomputing, vol. 435, pp. 197–215, 2021

    work page 2021

  14. [14]

    Guaranteed tensor recovery fused low-rankness and smoothness,

    H. Wang, J. Peng, W. Qin, J. Wang, and D. Meng, “Guaranteed tensor recovery fused low-rankness and smoothness,”IEEE Trans. Pattern Anal. Mach. Intell., vol. 45, no. 9, pp. 10 990–11 007, 2023

    work page 2023

  15. [15]

    Poisson tensor completion with transformed correlated total variation regularization,

    Q. Feng, J. Hou, W. Kong, C. Xu, and J. Wang, “Poisson tensor completion with transformed correlated total variation regularization,”Pattern Recognition, vol. 156, p. 110735, 2024

    work page 2024

  16. [16]

    Tensor completion using bilayer multimode low-rank prior and total variation,

    H. Zeng, S. Huang, Y . Chen, S. Liu, H. Q. Luong, and W. Philips, “Tensor completion using bilayer multimode low-rank prior and total variation,” IEEE Trans. Neural Networks Learn. Syst., vol. 35, no. 10, pp. 13 297–13 311, 2024

    work page 2024

  17. [17]

    Smooth parafac decomposition for tensor completion,

    T. Yokota, Q. Zhao, and A. Cichocki, “Smooth parafac decomposition for tensor completion,”IEEE Trans. on Signal Process., vol. 64, no. 20, pp. 5423–5436, 2016

    work page 2016

  18. [18]

    Fast and accurate tensor completion with total variation regularized tensor trains,

    C.-Y . Ko, K. Batselier, L. Daniel, W. Yu, and N. Wong, “Fast and accurate tensor completion with total variation regularized tensor trains,”IEEE Trans. on Image Process., vol. 29, pp. 6918–6931, 2020

    work page 2020

  19. [19]

    Tensor completion for estimating missing values in visual data,

    J. Liu, P. Musialski, P. Wonka, and J. Ye, “Tensor completion for estimating missing values in visual data,”IEEE Trans. Pattern Anal. Mach. Intell., vol. 35, no. 1, pp. 208–220, 2012

    work page 2012

  20. [20]

    Factorization strategies for third-order tensors,

    M. E. Kilmer and C. D. Martin, “Factorization strategies for third-order tensors,”Linear Algebra and Its Applications, vol. 435, no. 3, pp. 641–658, 2011

    work page 2011

  21. [21]

    Exact tensor completion using t-svd,

    Z. Zhang and S. Aeron, “Exact tensor completion using t-svd,”IEEE Trans. Signal Process., vol. 65, no. 6, pp. 1511–1526, 2016

    work page 2016

  22. [22]

    Tensor–tensor products with invertible linear transforms,

    E. Kernfeld, M. E. Kilmer, and S. Aeron, “Tensor–tensor products with invertible linear transforms,”Linear Algebra Appl., vol. 485, pp. 545–570, 2015

    work page 2015

  23. [23]

    Tensor completion by multi-rank via unitary transformation,

    G. Song, K. N. Michael, and X. Zhang, “Tensor completion by multi-rank via unitary transformation,”Appl. Comput. Harmon. Anal., vol. 65, pp. 348–373, 2023

    work page 2023

  24. [24]

    Nonlinear transform induced tensor nuclear norm for tensor completion,

    B.-Z. Li, X.-L. Zhao, T.-Y . Ji, X.-J. Zhang, and T.-Z. Huang, “Nonlinear transform induced tensor nuclear norm for tensor completion,”J. Sci. Comput., vol. 92, no. 83, p. 83, 2022

    work page 2022

  25. [25]

    Fundamental conditions for low-cp-rank tensor completion,

    M. Ashraphijuo and X. Wang, “Fundamental conditions for low-cp-rank tensor completion,”J. Mach. Learn. Res., vol. 18, no. 63, pp. 1–29, 2017

    work page 2017

  26. [26]

    Tensor svd: statistical and computational limits,

    A. Zhang and D. Xia, “Tensor svd: statistical and computational limits,”IEEE Trans. Inf. Theory, vol. 64, no. 11, pp. 7311–7338, 2018. 36

    work page 2018

  27. [27]

    Tensor factorization for low-rank tensor completion,

    P. Zhou, C. Lu, Z. Lin, and C. Zhang, “Tensor factorization for low-rank tensor completion,”IEEE Trans. Image Process., vol. 27, no. 3, pp. 1152–1163, 2017

    work page 2017

  28. [28]

    Noisy tensor completion via low-rank tensor ring,

    Y . Qiu, G. Zhou, Q. Zhao, and S. Xie, “Noisy tensor completion via low-rank tensor ring,”IEEE Trans. Neural Networks Learn. Syst., vol. 35, no. 1, pp. 1127 – 1141, 2024

    work page 2024

  29. [29]

    Low-rank tensor completion based on self-adaptive learnable transforms,

    T. Wu, B. Gao, J. Fan, J. Xue, and W. L. Woo, “Low-rank tensor completion based on self-adaptive learnable transforms,”IEEE Trans. Neural Networks Learn. Syst., vol. 35, no. 7, pp. 8826–8838, 2024

    work page 2024

  30. [30]

    Learnable spatial-spectral transform-based tensor nuclear norm for multi-dimensional visual data recovery,

    S. Liu, J. Leng, X.-L. Zhao, H. Zeng, Y . Wang, and J.-H. Yang, “Learnable spatial-spectral transform-based tensor nuclear norm for multi-dimensional visual data recovery,”IEEE Trans. Circuits Syst. Video Technol., vol. 34, no. 5, pp. 3633–3646, 2024

    work page 2024

  31. [31]

    A learnable group-tube transform induced tensor nuclear norm and its application for tensor completion,

    B.-Z. Li, X.-L. Zhao, X. Zhang, T.-Y . Ji, X. Chen, and M. K. Ng, “A learnable group-tube transform induced tensor nuclear norm and its application for tensor completion,”SIAM J. Imaging Sci., vol. 16, no. 3, pp. 1370–1397, 2023

    work page 2023

  32. [32]

    Attention-guided low-rank tensor completion,

    T. T. N. Mai, E. Y . Lam, and C. Lee, “Attention-guided low-rank tensor completion,”IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 46, no. 12, pp. 9818–9833, 2024

    work page 2024

  33. [33]

    1-bit tensor completion,

    A. Aidini, G. Tsagkatakis, and P. Tsakalides, “1-bit tensor completion,”Electronic Imaging, vol. 13, pp. 1–6, 2018

    work page 2018

  34. [34]

    Learning tensors from partial binary measurements,

    N. Ghadermarzy, Y . Plan, and O. Yilmaz, “Learning tensors from partial binary measurements,”IEEE Trans. Signal Process., vol. 67, no. 1, pp. 29–40, 2019

    work page 2019

  35. [35]

    One-bit tensor completion via transformed tensor singular value decomposition,

    J. Hou, F. Zhang, and J. Wang, “One-bit tensor completion via transformed tensor singular value decomposition,”Appl. Math. Model., vol. 95, no. 1, pp. 760–782, 2021

    work page 2021

  36. [36]

    1-bit tensor completion via max-and-nuclear-norm composite optimization,

    W. Cao, X. Chen, S. Yan, Z. Zhou, and A. Cichocki, “1-bit tensor completion via max-and-nuclear-norm composite optimization,”IEEE Trans. Signal Process., vol. 72, pp. 3487–3501, 2024

    work page 2024

  37. [37]

    Learning from binary multiway data: probabilistic tensor decomposition and its statistical optimality,

    M. Wang and L. Li, “Learning from binary multiway data: probabilistic tensor decomposition and its statistical optimality,”J. Mach. Learn. Res., vol. 21, no. 154, pp. 1—-38, 2020

    work page 2020

  38. [38]

    Low rank tensor completion with poisson observations,

    X. Zhang and M. K. Ng, “Low rank tensor completion with poisson observations,”IEEE Trans. Pattern Anal. Mach. Intell., vol. 44, no. 8, pp. 4239–4251, 2022

    work page 2022

  39. [39]

    Minimization of transformed l1 penalty: theory, difference of convex function algorithm, and robust application in compressed sensing,

    S. Zhang and J. Xin, “Minimization of transformed l1 penalty: theory, difference of convex function algorithm, and robust application in compressed sensing,”Mathematical Programming, vol. 169, no. 1, pp. 307–336, 2018

    work page 2018

  40. [40]

    Low-rank high-order tensor completion with applications in visual data,

    W. Qin, H. Wang, F. Zhang, J. Wang, X. Luo, and T. Huang, “Low-rank high-order tensor completion with applications in visual data,”IEEE Trans. Image Process., vol. 31, pp. 2433–2448, 2022

    work page 2022

  41. [41]

    Tensor compressive sensing fused low-rankness and local-smoothness,

    X. Liu, J. Hou, J. Peng, H. Wang, D. Meng, and J. Wang, “Tensor compressive sensing fused low-rankness and local-smoothness,”Proceedings of the AAAI Conference on Artificial Intelligence, vol. 37, no. 7, pp. 8879–8887, 2024

    work page 2024

  42. [42]

    Low rank matrix completion with exponential family noise,

    J. Lafond, “Low rank matrix completion with exponential family noise,” inProceedings of The 28th Conference on Learning Theory, vol. 40, 2015, pp. 1224–1243

    work page 2015

  43. [43]

    Collective matrix completion,

    M. Z. Alaya and O. Klopp, “Collective matrix completion,”Journal of Machine Learning Research, vol. 20, no. 148, pp. 1–43, 2019. [Online]. Available: http://jmlr.org/papers/v20/18-483.html

    work page 2019

  44. [44]

    Nonlocal tensor decomposition with joint low rankness and smoothness for spectral ct image reconstruction,

    C. Liu, S. Li, D. Hu, J. Wang, W. Qin, C. Liu, and P. Zhang, “Nonlocal tensor decomposition with joint low rankness and smoothness for spectral ct image reconstruction,”IEEE Trans. Comput. Imaging, vol. 10, pp. 613–627, 2024

    work page 2024

  45. [45]

    Tensor recovery from binary measurements fused low-rankness and smoothness,

    J. Hou, X. Liu, H. Wang, and K. Guo, “Tensor recovery from binary measurements fused low-rankness and smoothness,”Signal Processing, vol. 221, p. 109480, 2024

    work page 2024

  46. [46]

    Enhanced low-rank tensor recovery fusing reweighted tensor correlated total variation regularization for image denoising,

    K. Huang, W. Kong, M. Zhou, W. Qin, F. Zhang, and J. Wang, “Enhanced low-rank tensor recovery fusing reweighted tensor correlated total variation regularization for image denoising,”J. Sci. Comput., vol. 99, no. 3, p. 69, 2024

    work page 2024

  47. [47]

    B ¨uhlmann and S

    P. B ¨uhlmann and S. Van De Geer,Statistics for high-dimensional data: methods, theory and applications. Springer Science & Business Media, 2011

    work page 2011

  48. [48]

    Optimal rates for total variation denoising,

    J.-C. H ¨utter and P. Rigollet, “Optimal rates for total variation denoising,” in29th Annual Conference on Learning Theory, ser. Proceedings of Machine Learning Research, vol. 49, Columbia University, New York, USA, 23–26 Jun 2016, pp. 1115–1146. [Online]. Available: https://proceedings.mlr.press/v49/huetter16.html

    work page 2016

  49. [49]

    Distributed optimization and statistical learning via the alternating direction method of multipliers,

    S. Boyd, N. Parikh, E. Chu, B. Peleato, and J. Eckstein, “Distributed optimization and statistical learning via the alternating direction method of multipliers,”Found. Trends Mach. Learn., vol. 3, no. 1, pp. 1–122, 2011

    work page 2011

  50. [50]

    A max-norm constrained minimization approach to 1-bit matrix completion,

    T. Cai and W.-X. Zhou, “A max-norm constrained minimization approach to 1-bit matrix completion,”J. Mach. Learn. Res., vol. 14, pp. 3619–3647, 2013

    work page 2013

  51. [51]

    Adaptive rates for total variation image denoising,

    F. Ortelli and S. van de Geer, “Adaptive rates for total variation image denoising,”Journal of Machine Learning Research, vol. 21, no. 247, pp. 1–38,

    work page

  52. [52]

    Available: http://jmlr.org/papers/v21/20-301.html

    [Online]. Available: http://jmlr.org/papers/v21/20-301.html

    work page

  53. [53]

    One-bit total variation denoising over networks with applications to partially observed epidemics,

    C. Donnat, O. Klopp, and N. Verzelen, “One-bit total variation denoising over networks with applications to partially observed epidemics,”arXiv preprint arXiv:2405.00619, 2024

    work page arXiv 2024

  54. [54]

    Vershynin,High-Dimensional Probability: An Introduction with Applications in Data Science, ser

    R. Vershynin,High-Dimensional Probability: An Introduction with Applications in Data Science, ser. Cambridge Series in Statistical and Probabilistic Mathematics. Cambridge University Press, 2018

    work page 2018

  55. [55]

    Noisy low-rank matrix completion with general sampling distribution,

    O. Klopp, “Noisy low-rank matrix completion with general sampling distribution,”Bernoulli, vol. 20, no. 1, pp. 282–303, 2014. [Online]. Available: http://www.jstor.org/stable/42919393

    work page arXiv 2014

  56. [56]

    Adaptive multinomial matrix completion,

    O. Klopp, J. Lafond, ´E. Moulines, and J. Salmon, “Adaptive multinomial matrix completion,”Electron. J. Stat., vol. 9, no. 2, pp. 2950–2975, 2015

    work page 2015

  57. [57]

    Ledoux and M

    M. Ledoux and M. Talagrand,Probability in Banach Spaces: isoperimetry and processes. Springer Science & Business Media, 2013

    work page 2013

  58. [58]

    1-bit matrix completion,

    M. A. Davenport, Y . Plan, E. van den Berg, and M. Wootters, “1-bit matrix completion,”Information and Inference: A Journal of the IMA, vol. 3, no. 3, pp. 189 – 223, 2014

    work page 2014

  59. [59]

    A. B. Tsybakov,Nonparametric estimators. Springer, 2009

    work page 2009

  60. [60]

    Minimization of transformed penalty: Closed form representation and iterative thresholding algorithms,

    S. Zhang and J. Xin, “Minimization of transformed penalty: Closed form representation and iterative thresholding algorithms,”Communications in Mathematical Sciences, vol. 15, no. 2, pp. 511–537, 2017

    work page 2017