Zobrazeno 1 - 10
of 1 102
pro vyhledávání: '"Heinrich Stefan"'
Reinforcement learning policies are typically represented by black-box neural networks, which are non-interpretable and not well-suited for safety-critical domains. To address both of these issues, we propose constrained normalizing flow policies as
Externí odkaz:
http://arxiv.org/abs/2405.01198
Autor:
Heinrich, Stefan
Recently the adaption problem of Information-Based Complexity (IBC) for linear problems in the randomized setting was solved in Heinrich (J. Complexity 82, 2024, 101821). Several papers treating further aspects of this problem followed. However, all
Externí odkaz:
http://arxiv.org/abs/2401.14100
Reinforcement learning (RL) for complex tasks remains a challenge, primarily due to the difficulties of engineering scalar reward functions and the inherent inefficiency of training models from scratch. Instead, it would be better to specify complex
Externí odkaz:
http://arxiv.org/abs/2310.02360
Autor:
Heinrich Stefan, Lang Hauke
Publikováno v:
Innovative Surgical Sciences, Vol 2, Iss 1, Pp 1-8 (2017)
Liver surgery has become the standard treatment of primary liver cancer and liver metastases from colorectal cancer. Also, patients with non-colorectal liver metastases are increasingly offered surgery due to the low morbidity and excellent long-term
Externí odkaz:
https://doaj.org/article/362d9fb122e54fb1aabe4d151ce52fd6
Autor:
Heinrich, Stefan
We study the randomized $n$-th minimal errors (and hence the complexity) of vector valued approximation. In a recent paper by the author [Randomized complexity of parametric integration and the role of adaption I. Finite dimensional case (preprint)]
Externí odkaz:
http://arxiv.org/abs/2306.13697
Autor:
Heinrich, Stefan
We study the complexity of randomized computation of integrals depending on a parameter, with integrands from Sobolev spaces. That is, for $r,d_1,d_2\in{\mathbb N}$, $1\le p,q\le \infty$, $D_1= [0,1]^{d_1}$, and $D_2= [0,1]^{d_2}$ we are given $f\in
Externí odkaz:
http://arxiv.org/abs/2306.13499
Autor:
Heinrich, Stefan
We study the randomized $n$-th minimal errors (and hence the complexity) of vector valued mean computation, which is the discrete version of parametric integration. The results of the present paper form the basis for the complexity analysis of parame
Externí odkaz:
http://arxiv.org/abs/2306.13471
Furigana are pronunciation notes used in Japanese writing. Being able to detect these can help improve optical character recognition (OCR) performance or make more accurate digital copies of Japanese written media by correctly displaying furigana. Th
Externí odkaz:
http://arxiv.org/abs/2207.03960