Zobrazeno 1 - 10
of 19 160
pro vyhledávání: '"A, Ochs"'
Autor:
Sucker, Michael, Ochs, Peter
We present a probabilistic model for stochastic iterative algorithms with the use case of optimization algorithms in mind. Based on this model, we present PAC-Bayesian generalization bounds for functions that are defined on the trajectory of the lear
Externí odkaz:
http://arxiv.org/abs/2408.11629
In this paper, we aim to study non-convex minimization problems via second-order (in-time) dynamics, including a non-vanishing viscous damping and a geometric Hessian-driven damping. Second-order systems that only rely on a viscous damping may suffer
Externí odkaz:
http://arxiv.org/abs/2407.12518
Autor:
Ochs, Ian E.
Recent work has shown that synchrotron emission from relativistic plasmas leads the electron distribution to form an anisotropic ring in momentum space, which can be unstable to both kinetic and hydrodynamic instabilities. Fundamental to these works
Externí odkaz:
http://arxiv.org/abs/2407.13106
Synchrotron radiation losses are a significant cause of concern for high-temperature aneutronic fusion reactions such as proton-Boron 11. The fact that radiation losses occur primarily in the high-energy tail, where the radiation itself has a substan
Externí odkaz:
http://arxiv.org/abs/2407.09716
Our approach is part of the close link between continuous dissipative dynamical systems and optimization algorithms. We aim to solve convex minimization problems by means of stochastic inertial differential equations which are driven by the gradient
Externí odkaz:
http://arxiv.org/abs/2407.04562
Charged particles interacting with electromagnetic waves have a portion of their energy tied up in wave-driven oscillations. When these waves are localized to the exhaust of linear magnetic confinement systems this ponderomotive effect can be utilize
Externí odkaz:
http://arxiv.org/abs/2406.03727
Autor:
Castera, Camille, Ochs, Peter
Towards designing learned optimization algorithms that are usable beyond their training setting, we identify key principles that classical algorithms obey, but have up to now, not been used for Learning to Optimize (L2O). Following these principles,
Externí odkaz:
http://arxiv.org/abs/2405.18222
Quasi-Newton methods refer to a class of algorithms at the interface between first and second order methods. They aim to progress as substantially as second order methods per iteration, while maintaining the computational complexity of first order me
Externí odkaz:
http://arxiv.org/abs/2405.06824
Autor:
Heinrich, Marc, Zipfl, Maximilian, Uecker, Marc, Ochs, Sven, Gontscharow, Martin, Fleck, Tobias, Doll, Jens, Schörner, Philip, Hubschneider, Christian, Zofka, Marc René, Viehl, Alexander, Zöllner, J. Marius
Real world testing is of vital importance to the success of automated driving. While many players in the business design purpose build testing vehicles, we designed and build a modular platform that offers high flexibility for any kind of scenario. C
Externí odkaz:
http://arxiv.org/abs/2404.17550
We use the PAC-Bayesian theory for the setting of learning-to-optimize. To the best of our knowledge, we present the first framework to learn optimization algorithms with provable generalization guarantees (PAC-Bayesian bounds) and explicit trade-off
Externí odkaz:
http://arxiv.org/abs/2404.03290