paper-with-me

홈 › Papers

Unifying AMP Algorithms for Rotationally-Invariant Models

2024-12-02 · Songbin Liu, Junjie Ma

This paper presents a unified framework for constructing Approximate Message Passing (AMP) algorithms for rotationally-invariant models. By employing a general iterative algorithm template and reducing it to long-memory Orthogonal AMP (OAMP), we systematically derive the correct Onsager terms of AMP algorithms. This approach allows us to rederive an AMP algorithm introduced by Fan and Opper et al., while shedding new light on the role of free cumulants of the spectral law. The free cumulants arise naturally from a recursive centering operation, potentially of independent interest beyond the scope of AMP. To illustrate the flexibility of our framework, we introduce two novel AMP variants and apply them to estimation in spiked models.

📄 PDF Abstract BibTeX arXiv:2412.01574

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

AMP Based on the understanding that the flat local minima of the empirical risk cause the model to generalize better. Adversarial Model Perturbation (AMP) improves generalization via…

Similar Papers 제목 키워드 기반

Estimation in Rotationally Invariant Generalized Linear Models via Approximate Message Passing

2021-12-08 · Ramji Venkataramanan, Kevin Kögler, Marco Mondelli

We consider the problem of signal estimation in generalized linear models defined via rotationally invariant design matrices. Since these matrices can have an arbitrary spectral distribution, this model is well suited fo…

Optimality of Approximate Message Passing Algorithms for Spiked Matrix Models with Rotationally Invariant Noise

2024-05-28 · Rishabh Dudeja, Songbin Liu, Junjie Ma

We study the problem of estimating a rank one signal matrix from an observed matrix generated by corrupting the signal with additive rotationally invariant noise. We develop a new class of approximate message-passing alg…

Noise misleads rotation invariant algorithms on sparse targets

2024-03-05 · Manfred K. Warmuth, Wojciech Kotłowski, Matt Jones, Ehsan Amid

It is well known that the class of rotation invariant algorithms are suboptimal even for learning sparse linear problems when the number of examples is below the "dimension" of the problem. This class includes any gradie…

Approximate Message Passing for Multi-Layer Estimation in Rotationally Invariant Models

2022-12-03 · Yizhou Xu, Tianqi Hou, Shansuo Liang, Marco Mondelli

We consider the problem of reconstructing the signal and the hidden variables from observations coming from a multi-layer network with rotationally invariant weight matrices. The multi-layer structure models inference fr…

Orthogonal Approximate Message Passing Algorithms for Rectangular Spiked Matrix Models with Rotationally Invariant Noise

2026-02-03 · Haohua Chen, Songbin Liu, Junjie Ma arxiv

We propose an orthogonal approximate message passing (OAMP) algorithm for signal estimation in the rectangular spiked matrix model with general rotationally invariant (RI) noise. We establish a rigorous state evolution t…