A Bernstein inequality for exponentially growing graphs
نویسندگان
چکیده
منابع مشابه
a cauchy-schwarz type inequality for fuzzy integrals
نامساوی کوشی-شوارتز در حالت کلاسیک در فضای اندازه فازی برقرار نمی باشد اما با اعمال شرط هایی در مسئله مانند یکنوا بودن توابع و قرار گرفتن در بازه صفر ویک می توان دو نوع نامساوی کوشی-شوارتز را در فضای اندازه فازی اثبات نمود.
15 صفحه اولA Markov–Bernstein inequality for Gaussian networks
Let s ≥ 1 be an integer. A Gaussian network is a function on R of the form g(x) = ∑N k=1 ak exp(−‖x − xk‖ ). The minimal separation among the centers, defined by min1≤j 6=k≤N ‖xj − xk‖, is an important characteristic of the network that determines the stability of interpolation by Gaussian networks, the degree of approximation by such networks, etc. We prove that if g(x) = ∑N k=1 ak exp(−‖x − x...
متن کاملA Bernstein Theorem for Special Lagrangian Graphs
We obtain a Bernstein theorem for special Lagrangian graphs in Cn = R for arbitrary n only assuming bounded slope but no quantitative restriction.
متن کاملPAC-Bayes-Empirical-Bernstein Inequality
We present a PAC-Bayes-Empirical-Bernstein inequality. The inequality is based on a combination of the PAC-Bayesian bounding technique with an Empirical Bernstein bound. We show that when the empirical variance is significantly smaller than the empirical loss the PAC-Bayes-Empirical-Bernstein inequality is significantly tighter than the PAC-Bayes-kl inequality of Seeger (2002) and otherwise it ...
متن کاملA Sharp Bernstein-type Inequality for Exponential Sums
A subtle Bernstein-type extremal problem is solved by establishing the equality sup 06=f∈e E2n |f ′(0)| ‖f‖[−1,1] = 2n − 1 , where e E2n := ( f : f(t) = a0 + n X j=1 aje λjt + bje −λjt , aj , bj , λj ∈ R ) . This settles a conjecture of Lorentz and others and it is surprising to be able to provide a sharp solution. It follows fairly simply from the above that 1 e − 1 n − 1 min{y − a, b − y} ≤ s...
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: Communications in Statistics - Theory and Methods
سال: 2017
ISSN: 0361-0926,1532-415X
DOI: 10.1080/03610926.2017.1386317