Non-Asymptotic Confidence Regions for Errors-In-Variables Systems
Sign Up to like & getrecommendations! Published in 2018 at "IFAC-PapersOnLine"
DOI: 10.1016/j.ifacol.2018.09.060
Abstract: Abstract This paper deals with constructing non-asymptotic confidence regions for Errors-In-Variables (EIV) systems when there is noise on both the input and the output signal. The Leave-out Sign-dominant Correlation Regions (LSCR) approach originally devised for… read more here.
Keywords: errors variables; confidence; regions errors; confidence regions ... See more keywords
Non-asymptotic convergence analysis of inexact gradient methods for machine learning without strong convexity
Sign Up to like & getrecommendations! Published in 2017 at "Optimization Methods and Software"
DOI: 10.1080/10556788.2017.1296439
Abstract: Many recent applications in machine learning and data fitting call for the algorithmic solution of structured smooth convex optimization problems. Although the gradient descent method is a natural choice for this task, it requires exact… read more here.
Keywords: asymptotic convergence; machine learning; method; non asymptotic ... See more keywords
Non-asymptotic Confidence Regions for the Transfer Functions of Errors-in-Variables Systems
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Transactions on Automatic Control"
DOI: 10.1109/tac.2021.3080504
Abstract: Finite-sample system identification (FSID) methods provide guaranteed confidence regions for the unknown model parameter of dynamical systems under mild statistical assumptions for a finite number of data points. In this article, two FSID methods, the… read more here.
Keywords: non asymptotic; confidence; errors variables; eiv systems ... See more keywords
Non-Asymptotic Converse Bounds and Refined Asymptotics for Two Source Coding Problems
Sign Up to like & getrecommendations! Published in 2019 at "IEEE Transactions on Information Theory"
DOI: 10.1109/tit.2019.2920893
Abstract: In this paper, we revisit two multi-terminal lossy source coding problems: the lossy source coding problem with side information available at the encoder and one of the two decoders, which we term as the Kaspi… read more here.
Keywords: non asymptotic; source coding; problem; asymptotic converse ... See more keywords
Non-Asymptotic Bounds of Cumulant Generating Function of Codeword Lengths in Variable-Length Lossy Compression
Sign Up to like & getrecommendations! Published in 2023 at "IEEE Transactions on Information Theory"
DOI: 10.1109/tit.2022.3229358
Abstract: This paper investigates the problem of variable-length source coding with the criteria of the normalized cumulant generating function of codeword lengths and the excess distortion probability. We analyze the non-asymptotic fundamental limit of the normalized… read more here.
Keywords: non asymptotic; cumulant generating; codeword lengths; function codeword ... See more keywords
Non asymptotic controls on a recursive superquantile approximation
Sign Up to like & getrecommendations! Published in 2021 at "Electronic Journal of Statistics"
DOI: 10.1214/21-ejs1908
Abstract: In this work, we study a new recursive stochastic algorithm for the joint estimation of quantile and superquantile of an unknown distribution. The novelty of this algorithm is to use the Cesaro averaging of the… read more here.
Keywords: controls recursive; approximation; superquantile approximation; recursive superquantile ... See more keywords