Hessian spectrum at the global minimum of high-dimensional random landscapes
Hessian spectrum at the global minimum of high-dimensional random landscapes
复制标题
高维随机景观全局最小值处的 Hessian 谱
DOI:
10.1088/1751-8121/aae74f
复制
发表时间:
2018
期刊:
影响因子:
--
通讯作者:
P. Le Doussal
中科院分区:
文献类型:
--
作者:
Y. Fyodorov;P. Le Doussal
Using the replica method we calculate the mean spectral density of the Hessian matrix at the global minimum of a random dimensional isotropic, translationally invariant Gaussian random landscape confined by a parabolic potential with fixed curvature . Simple landscapes with generically a single minimum are typical for , and we show that the Hessian at the global minimum is always gapped, with the low spectral edge being strictly positive. When approaching from above the transitional point separating simple landscapes from ‘glassy’ ones, with exponentially abundant minima, the spectral gap vanishes as . For the Hessian spectrum is qualitatively different for ‘moderately complex’ and ‘genuinely complex’ landscapes. The former are typical for short-range correlated random potentials and correspond to one-step replica-symmetry breaking mechanism. Their Hessian spectra turn out to be again gapped, with the gap vanishing on approaching from below with a larger critical exponent, as . At the same time in the ‘most complex’ landscapes with long-ranged power-law correlations the replica symmetry is completely broken. We show that in that case the Hessian remains gapless for all values of , indicating the presence of ‘marginally stable’ spatial directions. Finally, the potentials with logarithmic correlations share both 1RSB nature and gapless spectrum. The spectral density of the Hessian always takes the semi-circular form, up to a shift and an amplitude that we explicitly calculate.
登录
查看更多内容
影响因子:
5.4
作者:
Yamada, Masaki;Vilenkin, Alexander
通讯作者:
Vilenkin, Alexander
影响因子:
3
作者:
Arguin, Louis-Pierre;Belius, David;Soundararajan, Kannan
通讯作者:
Soundararajan, Kannan
影响因子:
2.4
作者:
P. Littelmann;H.-J. Sommers;M.R. Zirnbauer
通讯作者:
M.R. Zirnbauer
DOI:
10.3150/17-bej964
发表时间:
2018
期刊:
Bernoulli : official journal of the Bernoulli Society for Mathematical Statistics and Probability
影响因子:
--
作者:
Cheng,Dan;Schwartzman,Armin
通讯作者:
Schwartzman,Armin