paper-with-me

홈 › Papers

On the phase diagram of extensive-rank symmetric matrix denoising beyond rotational invariance

2024-11-04 · Jean Barbier, Francesco Camilli, Justin Ko, Koki Okajima

Matrix denoising is central to signal processing and machine learning. Its statistical analysis when the matrix to infer has a factorised structure with a rank growing proportionally to its dimension remains a challenge, except when it is rotationally invariant. In this case the information theoretic limits and an efficient Bayes-optimal denoising algorithm, called rotational invariant estimator [1,2], are known. Beyond this setting few results can be found. The reason is that the model is not a usual spin system because of the growing rank dimension, nor a matrix model (as appearing in high-energy physics) due to the lack of rotation symmetry, but rather a hybrid between the two. Here we make progress towards the understanding of Bayesian matrix denoising when the signal is a factored matrix $XX^\intercal$ that is not rotationally invariant. Monte Carlo simulations suggest the existence of a \emph{denoising-factorisation transition} separating a phase where denoising using the rotational invariant estimator remains Bayes-optimal due to universality properties of the same nature as in random matrix theory, from one where universality breaks down and better denoising is possible, though algorithmically hard. We argue that it is only beyond the transition that factorisation, i.e., estimating $X$ itself, becomes possible up to irresolvable ambiguities. On the theory side, we combine mean-field techniques in an interpretable multiscale fashion in order to access the minimum mean-square error and mutual information. Interestingly, our alternative method yields equations reproducible by the replica approach of [3]. Using numerical insights, we delimit the portion of phase diagram where we conjecture the mean-field theory to be exact, and correct it using universality when it is not. Our complete ansatz matches well the numerics in the whole phase diagram when considering finite size effects.

📄 PDF Abstract BibTeX arXiv:2411.01974

Code (0)

등록된 구현이 없습니다.

Tasks

Denoising

Similar Papers 제목 키워드 기반

Causal Inference (C-inf) -- asymmetric scenario of typical phase transitions

2023-01-02 · Agostino Capponi, Mihailo Stojnic

In this paper, we revisit and further explore a mathematically rigorous connection between Causal inference (C-inf) and the Low-rank recovery (LRR) established in [10]. Leveraging the Random duality - Free probability th…

Causal Inference

Missing-Data-Induced Phase Transitions in Spectral PLS for Multimodal Learning

2026-01-29 · Anders Gjølbye, Ida Kargaard, Emma Kargaard, Lina Skerath 외 arxiv

Partial Least Squares (PLS) learns shared structure from paired data via the top singular vectors of the empirical cross-covariance (PLS-SVD), but multimodal datasets often have missing entries in both views. We study PL…

A Non-convex One-Pass Framework for Generalized Factorization Machine and Rank-One Matrix Sensing

2016-08-21 · NeurIPS 2016 12 · Ming Lin, Jieping Ye

We develop an efficient alternating framework for learning a generalized version of Factorization Machine (gFM) on steaming data with provable guarantees. When the instances are sampled from $d$ dimensional random Gaussi…

Matrix CompletionRetrieval

Projected Gradient Descent for Spectral Compressed Sensing via Symmetric Hankel Factorization

2024-03-14 · Jinsheng Li, Wei Cui, Xu Zhang

Current spectral compressed sensing methods via Hankel matrix completion employ symmetric factorization to demonstrate the low-rank property of the Hankel matrix. However, previous non-convex gradient methods only utiliz…

compressed sensingMatrix Completion

Guarantees of a Preconditioned Subgradient Algorithm for Overparameterized Asymmetric Low-rank Matrix Recovery

2024-10-22 · Paris Giampouras, HanQin Cai, Rene Vidal

In this paper, we focus on a matrix factorization-based approach to recover low-rank {\it asymmetric} matrices from corrupted measurements. We propose an {\it Overparameterized Preconditioned Subgradient Algorithm (OPSA)…