Zobrazeno 1 - 10
of 2 473
pro vyhledávání: '"f-divergences"'
A general reverse Pinsker's inequality is derived to give an upper bound on f-divergences in terms of total variational distance when two distributions are close measured under our proposed generalized local information geometry framework. In additio
Externí odkaz:
http://arxiv.org/abs/2406.00939
We study the problem of estimating the joint probability mass function (pmf) over two random variables. In particular, the estimation is based on the observation of $m$ samples containing both variables and $n$ samples missing one fixed variable. We
Externí odkaz:
http://arxiv.org/abs/2405.09523
Autor:
Nomura, Ryo, Yagi, Hideki
Two typical fixed-length random number generation problems in information theory are considered for general sources. One is the source resolvability problem and the other is the intrinsic randomness problem. In each of these problems, the optimum ach
Externí odkaz:
http://arxiv.org/abs/2404.11097
Most commonly used $f$-divergences of measures, e.g., the Kullback-Leibler divergence, are subject to limitations regarding the support of the involved measures. A remedy consists of regularizing the $f$-divergence by a squared maximum mean discrepan
Externí odkaz:
http://arxiv.org/abs/2402.04613
The solution to empirical risk minimization with $f$-divergence regularization (ERM-$f$DR) is presented under mild conditions on $f$. Under such conditions, the optimal measure is shown to be unique. Examples of the solution for particular choices of
Externí odkaz:
http://arxiv.org/abs/2402.00501
Autor:
Nomura, Ryo1 (AUTHOR) nomu@waseda.jp, Yagi, Hideki2 (AUTHOR) h.yagi@uec.ac.jp
Publikováno v:
Entropy. Sep2024, Vol. 26 Issue 9, p766. 34p.
Autor:
Martin, Micaela Y.1 (AUTHOR) micmarti@uji.es, Sbert, Mateu2 (AUTHOR) mateu.sbert@gmail.com, Chover, Miguel1 (AUTHOR) micmarti@uji.es
Publikováno v:
Entropy. Jun2024, Vol. 26 Issue 6, p464. 22p.
Goal-Conditioned Reinforcement Learning (RL) problems often have access to sparse rewards where the agent receives a reward signal only when it has achieved the goal, making policy optimization a difficult problem. Several works augment this sparse r
Externí odkaz:
http://arxiv.org/abs/2310.06794