Multidimensional Fourier series with quantum circuits
نویسندگان
چکیده
Quantum machine learning is the field that aims to integrate with quantum computation. In recent years, has emerged as an active research area potential bring new insights classical problems. One of challenges in explore expressibility parametrized circuits and their ability be universal function approximators, neural networks are. Recent works have shown that, a supervised model, we can fit any one-dimensional Fourier series, proving universality. However, models for multidimensional functions not been explored same level detail. this work, study various types circuit Ans\"atze generate series. We found some Ans\"atze, degrees freedom required fitting such grow faster than available Hilbert space generated by circuits. For example, single-qudit limited power represent arbitrary Despite this, show enlarge using more qudits or higher local dimensions meet requirements, thus ensuring universality models.
منابع مشابه
Energy Landscapes of Multidimensional Random Fourier Series
To any positive number ε and any nonnegative even Schwartz function w : R → R we associate the random function u on them-torus T := R/Z defined as the real part of the random Fourier series ∑ ~ν∈Zm X~ν,ε exp(2πi~ν · ~ θ), whereX~ν,ε are complex independent Gaussian random variables with variancew(ε|~ν|). LetN denote the number of critical points of u. We describe explicitly two constantsC,C′ su...
متن کاملLacunary Fourier Series for Compact Quantum Groups
This paper is devoted to the study of Sidon sets, Λ(p)-sets and some related notions for compact quantum groups. We establish several different characterizations of Sidon sets, and in particular prove that any Sidon set in a discrete group is a strong Sidon set in the sense of Picardello. We give several relations between Sidon sets, Λ(p)-sets and lacunarities for LFourier multipliers, generali...
متن کاملCritical Points of Multidimensional Random Fourier Series: Central Limits
We investigate certain families X~, 0 < ~ 1 of stationary Gaussian random smooth functions on the m-dimensional torus T := R/Z approaching the white noise as ~ → 0. We show that there exists universal constants c1, c2 > 0 such that for any cube B ⊂ R of size r ≤ 1/2, the number of critical points of X~ in the region B mod Z ⊂ T has mean ∼ c1 vol(B)~−m, variance ∼ c2 vol(B)~−m, and satisfies a c...
متن کاملCritical Points of Multidimensional Random Fourier Series: Variance Estimates
We investigate the number of critical points of a Gaussian random smooth function u on the m-torus T := R/Z. The randomness is specified by a fixed nonnegative Schwartz function w on the real axis and a small parameter ε so that, as ε → 0, the random function u becomes highly oscillatory and converges in a special fashion to the Gaussian white noise. Let N denote the number of critical points o...
متن کاملDetermination of a jump by Fourier and Fourier-Chebyshev series
By observing the equivalence of assertions on determining the jump of a function by its differentiated or integrated Fourier series, we generalize a previous result of Kvernadze, Hagstrom and Shapiro to the whole class of functions of harmonic bounded variation. This is achieved without the finiteness assumption on the number of discontinuities. Two results on determination of ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Physical review
سال: 2023
ISSN: ['0556-2813', '1538-4497', '1089-490X']
DOI: https://doi.org/10.1103/physreva.107.062612