Zobrazeno 1 - 10
of 545
pro vyhledávání: '"Li, XiangYuan"'
Autor:
Huang, De, Li, Xiangyuan
We establish non-asymptotic error bounds for the classical Maximal Likelihood Estimation of the transition matrix of a given Markov chain. Meanwhile, in the reversible case, we propose a new reversibility-preserving online Symmetric Counting Estimati
Externí odkaz:
http://arxiv.org/abs/2408.05963
Autor:
Huang, De, Li, Xiangyuan
We establish a new Bernstein-type deviation inequality for general discrete-time Markov chains via an elementary approach. More robust than existing works in the literature, our result only requires the Markov chain to satisfy an iterated Poincar\'e
Externí odkaz:
http://arxiv.org/abs/2408.04930
Self-supervised learning (SSL) has empirically shown its data representation learnability in many downstream tasks. There are only a few theoretical works on data representation learnability, and many of those focus on final data representation, trea
Externí odkaz:
http://arxiv.org/abs/2401.03214
Publikováno v:
In International Journal of Heat and Mass Transfer March 2025 238
Publikováno v:
In Coordination Chemistry Reviews 15 January 2025 523 Part 1
Publikováno v:
In Journal of the European Ceramic Society January 2025 45(1)
Publikováno v:
In Fuel 1 August 2024 369
Publikováno v:
In Fuel 15 June 2024 366
Etherification of biobased resveratrol with ethylene carbonate and its crosslinked polymethacrylates
Publikováno v:
In Materials Chemistry and Physics 1 April 2024 316
Publikováno v:
In Carbon 25 March 2024 222