Averaged Annealed Markov Chains Achieve the Algorithmic Threshold for Tensor PCA, Part I: Glauber Dynamics
Abstract
In the tensor principal components analysis (tensor PCA) problem, we are asked to recover an unknown vector in {±1}N from a noisy observation of its k-th tensor power, for a fixed k≥3. Tensor PCA exhibits a well-studied information-computation gap: global algorithms such as spectral methods and sum-of-squares work above an algorithmic threshold, below which we know matching lower bounds (against these and some other restricted models of computation). In contrast, local algorithms such as Markov chains were only known to succeed from a random initialization at a polynomially larger signal-to-noise ratio, and were believed to be inferior to global algorithms for tensor PCA. We show that Glauber dynamics, when supplemented with annealing and ergodic averaging, achieves polynomial-time strong recovery above the algorithmic threshold from a uniformly random initialization, demonstrating that local Markov chains can succeed all the way down to the algorithmic threshold from an uninformative cold start.
Related
- Averaged Annealed Markov Chains Achieve the Algorithmic Threshold for Tensor PCA, Part II: Langevin Dynamics
- Annealed Lévy Diffusion via Gaussian Surrogate Reverse Dynamics
- Annealed Underdamped Langevin Dynamics
- Algorithmic threshold for high-dimensional projection pursuit I: general theory
- Theoretical guidelines for annealed Langevin dynamics in compositional simulation-based inference
BibTeX
@misc{das2026averaged,
title = {{Averaged Annealed Markov Chains Achieve the Algorithmic Threshold for Tensor PCA, Part I: Glauber Dynamics}},
author = {Aniket Das and Tselil Schramm},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.16705},
eprint = {2610.16705},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.16705},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Averaged Annealed Markov Chains Achieve the Algorithmic Threshold for Tensor PCA, Part I: Glauber Dynamics
AU - Aniket Das
AU - Tselil Schramm
PY - 2026
DA - 2026/10/12
PB - arXiv
DO - 10.48550/arxiv.2610.16705
UR - https://arxiv.org/abs/2610.16705
AB - In the tensor principal components analysis (tensor PCA) problem, we are asked to recover an unknown vector in {±1}^N from a noisy observation of its k-th tensor power, for a fixed k≥3. Tensor PCA exhibits a well-studied information-computation gap: global algorithms such as spectral methods and sum-of-squares work above an algorithmic threshold, below which we know matching lower bounds (against these and some other restricted models of computation). In contrast, local algorithms such as Markov chains were only known to succeed from a random initialization at a polynomially larger signal-to-noise ratio, and were believed to be inferior to global algorithms for tensor PCA. We show that Glauber dynamics, when supplemented with annealing and ergodic averaging, achieves polynomial-time strong recovery above the algorithmic threshold from a uniformly random initialization, demonstrating that local Markov chains can succeed all the way down to the algorithmic threshold from an uninformative cold start.
ER -