REVIEW 4 cited by
A Non-Asymptotic Framework for Approximate Message Passing in Spiked Models
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
abstract
Approximate message passing (AMP) emerges as an effective iterative paradigm for solving high-dimensional statistical problems. However, prior AMP theory -- which focused mostly on high-dimensional asymptotics -- fell short of predicting the AMP dynamics when the number of iterations surpasses $o\big(\frac{\log n}{\log\log n}\big)$ (with $n$ the problem dimension). To address this inadequacy, this paper develops a non-asymptotic framework for understanding AMP in spiked matrix estimation. Built upon new decomposition of AMP updates and controllable residual terms, we lay out an analysis recipe to characterize the finite-sample behavior of AMP in the presence of an independent initialization, which is further generalized to allow for spectral initialization. As two concrete consequences of the proposed analysis recipe: (i) when solving $\mathbb{Z}_2$ synchronization, we predict the behavior of spectrally initialized AMP for up to $O\big(\frac{n}{\mathrm{poly}\log n}\big)$ iterations, showing that the algorithm succeeds without the need of a subsequent refinement stage (as conjectured recently by \citet{celentano2021local}); (ii) we characterize the non-asymptotic behavior of AMP in sparse PCA (in the spiked Wigner model) for a broad range of signal-to-noise ratio.
Forward citations
Cited by 4 Pith papers
-
Approximate Message Passing with Random Initialization for Phase Retrieval
Randomly initialized Bayes-optimal AMP provably achieves the weak-recovery threshold δ=1/2 and arbitrarily accurate recovery for δ>1.13 in proportional-regime noiseless phase retrieval.
-
Markov Chains Approximate Message Passing
For spiked Wigner inference, Glauber dynamics and AMP reach the same correlation fixed point, with a phase transition at βλ=1 conditional on SK mixing.
-
Scaling Laws and Spectra of Shallow Neural Networks in the Feature Learning Regime
For diagonal and quadratic two-layer networks, training maps to LASSO and matrix compressed sensing, yielding a full phase diagram of excess-risk scaling exponents and a spectral characterization of the trained weights.
-
Multi-Environment GLAMP: Approximate Message Passing for Transfer Learning with Applications to Lasso-based Estimators
Multi-environment GLAMP yields exact asymptotic risk formulas for three Lasso-based transfer learning estimators under Gaussian designs, validated by simulations.
Discussion (0). Continue with ORCID to comment.