- Rating
- 3(+1)
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 1
- Soundness
- 3
Read review
Paper summary
This paper studies identifiability of the so-called Bhattacharya–Mesner (BM) decomposition of a tensor. Specifically, local identifiability is characterized by studying the kernel of the Jacobian of the map that sends a parameter vector into its corresponding tensor. This kernel contains directions that are due to inherent scaling ambiguities, which are not harmful for essential uniqueness, but may contain others if the decomposition is not locally unique. The authors then capitalize on this analysis to derive error bounds on decomposition factors due to a perturbation. They also give a template of cases in which local essential uniqueness is violated, and a proof of global essential uniqueness in the rank-one case.
Despite the relevance of the presented results, the manuscript suffers from various significant drawbacks, as discussed below. First, in my view it fails to describe exactly how it fits in the literature, how it connects to prior results, and which gaps it fulfills. Second, there are substantial presentation issues, related to the clarity and proper formalization of its contents.
Critical strengths
- The paper's results represent one non-negligible (albeit moderate) step towards understanding the identifiability of the BM model.
Critical weaknesses
- The paper suffers from severe lack of clarity. Many important elements and information are left implicit, or are discussed using informal or otherwise undefined expressions, leaving the reader to try and connect the dots too often. For instance:
- What are separable template ratios?
- What is the dimension ceiling?
- Is X^{(j) a tensor slice?
- What is the definition of in Definition 1?
- What is the meaning of the symbol that appears in (4) before ?
- The identity appears before giving any definition or explanation of what the factors in the left-hand side mean.
- What are anchor entries?
- What is exactly the definition of ?
- What is a locally constant-rank point?
- What is the "stated obstruction" of line 140?
- What is the "fixed-template mixing family" of Theorem 7?
- Why is Gaussian elimination performed in 6.1 modulo the prime q=1,000,003?
- The experiment whose results are presented in Section 6.2 has to be explained carefully. What is being done exactly?
- What does the phrase "The template-transition experiment perturbs a separable ratio" mean?
-
Citations and proper discussion on relation to prior literature are often missing as well. To give an important example, no reference is given for the BM decomposition (the main object of this paper) in the Introduction.
-
There is insufficient historical contextualization and discussion on prior contributions to tensor decomposition identifiability, and on how the currently presented results related to them. The authors have certainly been inspired or otherwise informed by existing papers on CP identifiability, for instance. But this discussion is completely absent from the text, apart from a very succinct mention of some references in Section 7. Even this part misses a very important and definitely related reference, namely "Generic and typical ranks of multi-way arrays" by P. Comon et al., who have measured the dimension of the tangent space at a generic point, for the CP parametrization of a tensor with a given rank.
-
The paper falls short of giving conditions for global essential uniqueness, apart from the rank-one case.
Questions for authors
-
Certain results seem to follow quite standard arguments, which are not specific to the studied BM decomposition. For instance, wouldn't Proposition 5 also hold say, for the CP decomposition, with the appropriate changes in the involved objects? Has some similar result been stated in the literature for other tensor decompositions? If so, they have to be cited and discussed here as inspiration for your own developments.
-
Given that there is plenty of space in the 9th page, why not write some of the proofs in their full form? In particular, some of them are not much longer than their respective sketches given in the main text. One example is the proof of Theorem 3. This would help mitigating the clarity issues raised in the "Weaknesses" part.
2 comments
I appreciate the authors' efforts in improving the readability of this paper. In consonance, I am upgrading my evaluation.
Thank you for your comments; we respond below and have revised the manuscript accordingly.
Definitions and experimental clarity. Appendix A now starts with a notation table. The 33, two-term example in Section 2 contrasts inverse column rescaling, which preserves each component, with a shear changing {1,1} to {1−ϵ,1+ϵ} at fixed sum. --Separable template ratios. This means rank(At⊘A1)=1, equivalently At=A1⊙ρ(t)σ(t)⊤ (Abstract and Section 4).
--Dimension ceiling. The necessary parameter-count ceiling is r⋆=⌊mpn/(mn+mp+pn−m−p−n+1)⌋ (Abstract and Section 3).
--Tensor slice. X(j)=X:,j,:∈Fm×n is a lateral slice. It is defined in Section 2 after (2).
--Parameter space. We now write the parameter space as Θr, with Θr=(F×)r(mn+mp+pn) (Section 2).
--Semidirect product. In Gr≅(F×)r(m+p+n−1)⋊Sr, Sr permutes the component scaling blocks (Section 2).
--Factor ratios. For fixed t, define Uik=Aitk/Aitk, Vij=Bijt/Bijt, and Wjk=Ctjk/Ctjk before using UikVijWjk=1.
--Anchors. We fix Ait1=A1tk=B1jt=1.
--Normalized map. Fill the anchors with ones to obtain θ(z); z∈(F×)d holds the remaining entries. Then F(z)=Φr(θ(z))∈Fm×p×n (Section 2).
--Locally constant-rank point. Here rankDF is constant in a neighborhood.
--Stated obstruction. It is d≤mpn, assuming local constant rank over R (Section 3).
--Fixed-template mixing family. Vary Sj∈GLr independently in P(j)Sj, Q(j)Sj−⊤ at fixed At. Dimension is modulo gauge and permutations (Section 4).
--Modular elimination. With q=1,000,003, elimination is exact. A minor nonzero modulo a prime is nonzero in characteristic zero. Attaining min(d,mpn) certifies exact rank without floating-point tolerances; any prime preserving the minor suffices.
--Section 6.2 experiment. Section 6.2 applies the shear to the Appendix C factors, normalizes them, and compares factor variation with unchanged reconstruction; the rank check is reported there.
--Template-transition experiment. We perturb A2=A1⊙(ρσ⊤+ηN) away from separability and track reduced-Jacobian rank. Sections 6.2 and H.1/H.4 give the sampling protocol, spectra, and tolerance-dependent thresholds; Figure 3(b) shows a separate transition experiment.
BM model attribution. The introduction now cites Mesner--Bhattacharya (1990, 1994) and Gnang--Filmus (2020) when introducing BM, and Tian et al. (2025) for video applications.
Earlier identifiability methods. Sections 1 and 7 relate the BM monomial parameterization to the no-three-way-interaction toric model. Over C, the Zariski closure of sums of r components is its affine secant cone. Terracini gives its generic tangent space as the sum of component tangent spaces. We cite Landsberg (2012), Comon, ten Berge, De Lathauwer and Castaing (2009), and Chiantini and collaborators on CP identifiability. Full-column-rank tests certify nondefectivity and local, not global, uniqueness in the admissible range. Scaling-fiber and inverse-function tools are standard; the effective gauge, canonical section, and slice-mixing families are specific to BM. Appendix B extends existing certificates to infinite shape families. The positive 53,r=2 ambiguity is a special locus in a generically locally identifiable shape. CP can also have exceptional ambiguous points.
Global essential uniqueness. Our global result is confined to rank one. At higher rank, we establish local identifiability only. Section 8 now states explicitly that distinct isolated decompositions of the same tensor are not excluded. A general higher-rank global uniqueness theorem remains open; we make no claim beyond the local certificates.
Perturbation theory. Yes. Proposition 5 applies the implicit function theorem to local least squares, as for CP or any smooth map with full-column-rank derivative. We cite Breiding--Vannieuwenhoven (2018) on join-decomposition conditioning. BM supplies the normalized coordinates and structural obstructions; singular values depend on these coordinates. The local perturbation bound has a quadratic remainder. The residual-to-factor bound requires a Lipschitz radius; neither guarantees global optimization.
Complete proofs. Section 3 gives the full proof of Theorem 3 via the normalized section, finite permutation orbit, inverse function theorem, and constant-rank converse. Section 4 gives the full proof of Theorem 7, with the non-gauge shear, residual diagonal action, and quotient dimension. The notation table and example define the objects used.