REVIEW 4 cited by
Spectral Phase Transitions in Non-Linear Wigner 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
We study the asymptotic behavior of the spectrum of a random matrix where a non-linearity is applied entry-wise to a Wigner matrix perturbed by a rank-one spike with independent and identically distributed entries. In this setting, we show that when the signal-to-noise ratio scale as $N^{\frac{1}{2} (1-1/k_\star)}$, where $k_\star$ is the first non-zero generalized information coefficient of the function, the non-linear spike model effectively behaves as an equivalent spiked Wigner matrix, where the former spike before the non-linearity is now raised to a power $k_\star$. This allows us to study the phase transition of the leading eigenvalues, generalizing part of the work of Baik, Ben Arous and Pech\'e to these non-linear models.
Forward citations
Cited by 4 Pith papers
-
Fluctuations of the largest eigenvalues of transformed spiked Wigner matrices
The largest eigenvalue of an entrywise-transformed spiked Wigner matrix has the same fluctuation law as a standard spiked Wigner matrix, with the effective SNR λ(E[f'])^2 replacing λ.
-
On The Concurrence of Layer-wise Preconditioning Methods and Provable Feature Learning
For two feature-learning models with anisotropic inputs, KFAC-style layer-wise preconditioning provably recovers features better than SGD and matches ridge regression in the single-index case.
-
On the Mechanisms of Weak-to-Strong Generalization: A Theoretical Perspective
In high-dimensional linear and one-step feature-learning models, a regularized student can outperform its teacher by fixing under-regularization, using better regularization structure, or retaining pretrained hard features.
-
Optimal Spectral Transitions in High-Dimensional Multi-Index Models
Two linearized message-passing spectral estimators achieve the optimal weak-recovery threshold in Gaussian multi-index models, with a sharp BBP-like spectral phase transition at the critical sample complexity.
Discussion (0). Continue with ORCID to comment.