Zobrazeno 1 - 10
of 3 215
pro vyhledávání: '"Reeb A"'
Autor:
Flynn, Hamish, Reeb, David
Confidence bounds are an essential tool for rigorously quantifying the uncertainty of predictions. They are a core component in many sequential learning and decision-making algorithms, with tighter confidence bounds giving rise to algorithms with bet
Externí odkaz:
http://arxiv.org/abs/2403.12732
Publikováno v:
Neuromorphic Computing and Engineering (2023)
Processing sensor data with spiking neural networks on digital neuromorphic chips requires converting continuous analog signals into spike pulses. Two strategies are promising for achieving low energy consumption and fast processing speeds in end-to-
Externí odkaz:
http://arxiv.org/abs/2310.02055
Publikováno v:
Published paper: https://openreview.net/forum?id=TXoZiUZywf | Oral presentation: https://neurips.cc/virtual/2023/oral/73845
We present improved algorithms with worst-case regret guarantees for the stochastic linear bandit problem. The widely used "optimism in the face of uncertainty" principle reduces a stochastic bandit problem to the construction of a confidence sequenc
Externí odkaz:
http://arxiv.org/abs/2309.14298
Autor:
Randrianarimanana, Rivoharifara, Rakotondrainibe, France, Boucheron-Dubuisson, Elodie, Marline, Lovanomenjanahary, Rakotoarinivo, Mijoro, Reeb, Catherine
Publikováno v:
Plant Ecology and Evolution, 2024 Jan 01. 157(1), 3-19.
Externí odkaz:
https://www.jstor.org/stable/48770167
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2023
PAC-Bayes has recently re-emerged as an effective theory with which one can derive principled learning algorithms with tight performance guarantees. However, applications of PAC-Bayes to bandit problems are relatively rare, which is a great misfortun
Externí odkaz:
http://arxiv.org/abs/2211.16110
Publikováno v:
Proceedings of the Thirty-Ninth Conference on Uncertainty in Artificial Intelligence (UAI 2023), PMLR 216:1730-1740, 2023, URL: https://proceedings.mlr.press/v216/reeb23a.html
Assessing the validity of a real-world system with respect to given quality criteria is a common yet costly task in industrial applications due to the vast number of required real-world tests. Validating such systems by means of simulation offers a p
Externí odkaz:
http://arxiv.org/abs/2210.12061
Autor:
Haefliger, André, Reeb, Georges
The original article titled "Vari\'et\'es (non s\'epar\'ees) \`a une dimension et structures feuillet\'ees du plan" was published in 1957 in French in L'Enseignement Math\'ematique. It establishes a beautiful connection between foliations of the plan
Externí odkaz:
http://arxiv.org/abs/2208.11193
Publikováno v:
Review of Accounting Studies. Dec2024, Vol. 29 Issue 4, p3019-3052. 34p.
Publikováno v:
Proceedings of the 39th International Conference on Machine Learning (ICML), PMLR 162:16969-16989, 2022
We present an approach that incorporates expert knowledge for time-series representation learning. Our method employs expert features to replace the commonly used data transformations in previous contrastive learning approaches. We do this since time
Externí odkaz:
http://arxiv.org/abs/2206.11517
Autor:
Reeb, Katelyn L., Wiah, Sonita, Patel, Bhumiben P., Lewandowski, Stacia I., Mortensen, Ole V., Salvino, Joseph M., Rawls, Scott M., Fontana, Andréia C.K.
Publikováno v:
In European Journal of Pharmacology 5 December 2024 984