Preprint · 2025 · Open access
Computational Thresholds in Multi-Modal Learning via the Spiked Matrix-Tensor Model
arXiv (Cornell University) · Published 3 June 2025 · DOI 10.48550/arxiv.2506.02664
In brief
“Computational Thresholds in Multi-Modal Learning via the Spiked Matrix-Tensor Model” is a 2025 preprint by Hugo Tabanelli and 3 co-authors, published in arXiv (Cornell University). OpenAlex counts 7 citations as of 18 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).
- Citations
- 7
- Most cited in
- 2026 (6)
- References
- 31
- Authors
- 4
Abstract
We study the recovery of multiple high-dimensional signals from two noisy, correlated modalities: a spiked matrix and a spiked tensor sharing a common low-rank structure. This setting generalizes classical spiked matrix and tensor models, unveiling intricate interactions between inference channels and surprising algorithmic behaviors. Notably, while the spiked tensor model is typically intractable at low signal-to-noise ratios, its correlation with the matrix enables efficient recovery via Bayesian Approximate Message Passing, inducing staircase-like phase transitions reminiscent of neural network phenomena. In contrast, empirical risk minimization for joint learning fails: the tensor component obstructs effective matrix recovery, and joint optimization significantly degrades performance, highlighting the limitations of naive multi-modal learning. We show that a simple Sequential Curriculum Learning strategy-first recovering the matrix, then leveraging it to guide tensor recovery-resolves this bottleneck and achieves optimal weak recovery thresholds. This strategy, implementable with spectral methods, emphasizes the critical role of structural correlation and learning order in multi-modal high-dimensional inference.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Tabanelli, H., Mergny, P., Zdeborová, L., & Krząkała, F. (2025). Computational Thresholds in Multi-Modal Learning via the Spiked Matrix-Tensor Model. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2506.02664
MLA 9
Tabanelli, Hugo, et al. “Computational Thresholds in Multi-Modal Learning via the Spiked Matrix-Tensor Model.” arXiv (Cornell University), 2025. https://doi.org/10.48550/arxiv.2506.02664.
Chicago
Tabanelli, Hugo, Pierre Mergny, Lenka Zdeborová, and Florent Krząkała. 2025. “Computational Thresholds in Multi-Modal Learning via the Spiked Matrix-Tensor Model.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2506.02664.
Harvard
Tabanelli, H. et al. (2025) ‘Computational Thresholds in Multi-Modal Learning via the Spiked Matrix-Tensor Model’, arXiv (Cornell University). doi:10.48550/arxiv.2506.02664.
IEEE
H. Tabanelli, P. Mergny, L. Zdeborová, and F. Krząkała, “Computational Thresholds in Multi-Modal Learning via the Spiked Matrix-Tensor Model,” arXiv (Cornell University), 2025, doi: 10.48550/arxiv.2506.02664.
BibTeX
@misc{tabanelli2025computational,
title = {{Computational Thresholds in Multi-Modal Learning via the Spiked Matrix-Tensor Model}},
author = {Tabanelli, Hugo and Mergny, Pierre and Zdeborová, Lenka and Krząkała, Florent},
howpublished = {arXiv (Cornell University)},
year = {2025},
doi = {10.48550/arxiv.2506.02664},
url = {https://doi.org/10.48550/arxiv.2506.02664}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Physical Sciences › Computer Science › Signal Processing › Sparse and Compressive Sensing Techniques
- multimodal learning
- empirical risk minimization
- spectral methods
- high-dimensional inference
- signal-to-noise ratio
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Tabanelli, H., Mergny, P., Zdeborová, L., & Krząkała, F. (2025). Computational Thresholds in Multi-Modal Learning via the Spiked Matrix-Tensor Model. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2506.02664
How many times has this paper been cited?
7 times, according to OpenAlex on 18 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access at arXiv (Cornell University): sign in and open the PDF from this page.
Who wrote this paper?
Hugo Tabanelli, Pierre Mergny, Lenka Zdeborová, Florent Krząkała.
What is the DOI of this paper?
10.48550/arxiv.2506.02664, permanently at https://doi.org/10.48550/arxiv.2506.02664. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 18 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.