Zobrazeno 1 - 10
of 498
pro vyhledávání: '"62M45"'
Autor:
Csanády, Bálint, Nagy, Lóránt, Boros, Dániel, Ivkovic, Iván, Kovács, Dávid, Tóth-Lakits, Dalma, Márkus, László, Lukács, András
We present a purely deep neural network-based approach for estimating long memory parameters of time series models that incorporate the phenomenon of long-range dependence. Parameters, such as the Hurst exponent, are critical in characterizing the lo
Externí odkaz:
http://arxiv.org/abs/2410.03776
Publikováno v:
Lecture Notes in Computer Science, volume 13621, International Conference on Learning and Intelligent Optimization 2022
The advances and development of various machine learning techniques has lead to practical solutions in various areas of science, engineering, medicine and finance. The great choice of algorithms, their implementations and libraries has resulted in an
Externí odkaz:
http://arxiv.org/abs/2410.01831
The Statistical Classification of Economic Activities in the European Community (NACE) is the standard classification system for the categorization of economic and industrial activities within the European Union. This paper proposes a novel approach
Externí odkaz:
http://arxiv.org/abs/2409.11524
Autor:
Della Libera, Luca
Recent advances in deep reinforcement learning have achieved impressive results in a wide range of complex tasks, but poor sample efficiency remains a major obstacle to real-world deployment. Soft actor-critic (SAC) mitigates this problem by combinin
Externí odkaz:
http://arxiv.org/abs/2409.04971
Autor:
Chen, Yuan, Xiu, Dongbin
We present a numerical method for learning the dynamics of slow components of unknown multiscale stochastic dynamical systems. While the governing equations of the systems are unknown, bursts of observation data of the slow variables are available. B
Externí odkaz:
http://arxiv.org/abs/2408.14821
Let $\Omega\subset \mathbb{R}^d$ be a bounded domain. We consider the problem of how efficiently shallow neural networks with the ReLU$^k$ activation function can approximate functions from Sobolev spaces $W^s(L_p(\Omega))$ with error measured in the
Externí odkaz:
http://arxiv.org/abs/2408.10996
Autor:
Nelsen, Nicholas H., Stuart, Andrew M.
Publikováno v:
SIAM Review Vol. 66 No. 3 (2024) pp. 535-571
Supervised operator learning centers on the use of training data, in the form of input-output pairs, to estimate maps between infinite-dimensional spaces. It is emerging as a powerful tool to complement traditional scientific computing, which may oft
Externí odkaz:
http://arxiv.org/abs/2408.06526
Autor:
Chen, Thomas, Ewald, Patrícia Muñoz
We prove that the usual gradient flow in parameter space that underlies many training algorithms for neural networks in deep learning can be continuously deformed into an adapted gradient flow which yields (constrained) Euclidean gradient flow in out
Externí odkaz:
http://arxiv.org/abs/2408.01517
Autor:
Bongratz, Fabian, Golkov, Vladimir, Mautner, Lukas, Della Libera, Luca, Heetmeyer, Frederik, Czaja, Felix, Rodemann, Julian, Cremers, Daniel
The field of reinforcement learning offers a large variety of concepts and methods to tackle sequential decision-making problems. This variety has become so large that choosing an algorithm for a task at hand can be challenging. In this work, we stre
Externí odkaz:
http://arxiv.org/abs/2407.20917
Autor:
Staněk, Filip
This article describes the methods that achieved 4th and 6th place in the forecasting and investment challenges, respectively, of the M6 competition, ultimately securing the 1st place in the overall duathlon ranking. In the forecasting challenge, we
Externí odkaz:
http://arxiv.org/abs/2407.20352