Complexity of local maxima of given radial derivative for mixed $p$-spin Hamiltonians
David Belius, Marius A. Schmidt

TL;DR
This paper proves that the expected number of local maxima with a given radial derivative in mixed p-spin models exhibits a second moment matching the square of the first moment on an exponential scale, indicating concentration.
Contribution
It establishes a general result for mixed p-spin models, showing the second moment matches the first moment squared for local maxima with a specified radial derivative, extending previous specific cases.
Findings
Second moment matches the square of the first moment on exponential scale.
Derived formulas for moments using Kac-Rice computations.
Provided a new proof of a key inequality without computer assistance.
Abstract
We study the number of local maxima with given radial derivative of spherical mixed -spin models and prove that the second moment matches the square of the first moment on exponential scale for arbitrary mixtures and any radial derivative. This is surprising, since for the number of local maxima with given radial derivative and given energy the corresponding result is only true for specific mixtures [Sub17; BSZ20]. We use standard Kac-Rice computations to derive formulas for the first and second moment at exponential scale, and then find a remarkable analytic argument that shows that the second moment formula is bounded by twice the first moment formula in this general setting. This also leads to a new proof of a central inequality used to prove concentration of the number critical points of pure -spin models of given energy in [Sub17] and removes the need for the computer…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsMarkov Chains and Monte Carlo Methods · Stochastic processes and statistical mechanics · Random Matrices and Applications
