Sharper Bounds for Gaussian and Empirical Processes
نویسندگان
چکیده
منابع مشابه
Sharper ABC-based bounds for congruent polynomials
Agrawal, Kayal, and Saxena recently introduced a new method of proving that an integer is prime. The speed of the Agrawal-Kayal-Saxena method depends on proven lower bounds for the size of the multiplicative semigroup generated by several polynomials modulo another polynomial h. Voloch pointed out an application of the Stothers-Mason ABC theorem in this context: under mild assumptions, distinct...
متن کاملSharper Bounds for Regularized Data Fitting
We study matrix sketching methods for regularized variants of linear regression, low rank approximation, and canonical correlation analysis. Our main focus is on sketching techniques which preserve the objective function value for regularized problems, which is an area that has remained largely unexplored. We study regularization both in a fairly broad setting, and in the specific context of th...
متن کاملThe Rate of Entropy for Gaussian Processes
In this paper, we show that in order to obtain the Tsallis entropy rate for stochastic processes, we can use the limit of conditional entropy, as it was done for the case of Shannon and Renyi entropy rates. Using that we can obtain Tsallis entropy rate for stationary Gaussian processes. Finally, we derive the relation between Renyi, Shannon and Tsallis entropy rates for stationary Gaussian proc...
متن کاملLarge deviations bounds for empirical processes
Vapnik-Chervonenkis bounds on speeds of convergence of empirical means to their expectations have been continuously improved over the years. The result obtained by M. Talagrand in 1994 11] seems to provide the nal word as far as universal bounds are concerned. However, for xed families of underlying probability distributions, the exponential rate in the deviation term can be fairly improved by ...
متن کاملSharper Bounds for Regression and Low-Rank Approximation with Regularization
We study matrix sketching methods for regularized variants of linear regression, low rank approximation, and canonical correlation analysis. Our main focus is on sketching techniques which preserve the objective function value for regularized problems, which is an area that has remained largely unexplored. We study regularization both in a fairly broad setting, and in the specific context of th...
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: The Annals of Probability
سال: 1994
ISSN: 0091-1798
DOI: 10.1214/aop/1176988847