Zobrazeno 1 - 10
of 19 215
pro vyhledávání: '"A, Ochs"'
Autor:
Orf, Stefan, Ochs, Sven, Doll, Jens, Schotschneider, Albert, Heinrich, Marc, Zofka, Marc René, Zöllner, J. Marius
Fault diagnosis is crucial for complex autonomous mobile systems, especially for modern-day autonomous driving (AD). Different actors, numerous use cases, and complex heterogeneous components motivate a fault diagnosis of the system and overall syste
Externí odkaz:
http://arxiv.org/abs/2411.09643
Autor:
Ochs, Sebastian, Habernal, Ivan
How capable are diffusion models of generating synthetics texts? Recent research shows their strengths, with performance reaching that of auto-regressive LLMs. But are they also good in generating synthetic data if the training was under differential
Externí odkaz:
http://arxiv.org/abs/2410.22971
Autor:
Ochs, Sven, Yazgan, Melih, Polley, Rupert, Schotschneider, Albert, Orf, Stefan, Uecker, Marc, Zipfl, Maximilian, Burger, Julian, Vivekanandan, Abhishek, Amritzer, Jennifer, Zofka, Marc René, Zöllner, J. Marius
As cities strive to address urban mobility challenges, combining autonomous transportation technologies with intelligent infrastructure presents an opportunity to transform how people move within urban environments. Autonomous shuttles are particular
Externí odkaz:
http://arxiv.org/abs/2410.20989
Autor:
Mehmood, Sheheryar, Ochs, Peter
Numerous Optimization Algorithms have a time-varying update rule thanks to, for instance, a changing step size, momentum parameter or, Hessian approximation. In this paper, we apply unrolled or automatic differentiation to a time-varying iterative pr
Externí odkaz:
http://arxiv.org/abs/2410.15923
In this paper, we propose two regularized proximal quasi-Newton methods with symmetric rank-1 update of the metric (SR1 quasi-Newton) to solve non-smooth convex additive composite problems. Both algorithms avoid using line search or other trust regio
Externí odkaz:
http://arxiv.org/abs/2410.11676
Autor:
Sucker, Michael, Ochs, Peter
Convergence in learning-to-optimize is hardly studied, because conventional convergence guarantees in optimization are based on geometric arguments, which cannot be applied easily to learned algorithms. Thus, we develop a probabilistic framework that
Externí odkaz:
http://arxiv.org/abs/2410.07704
Research on non-verbal behavior generation for social interactive agents focuses mainly on the believability and synchronization of non-verbal cues with speech. However, existing models, predominantly based on deep learning architectures, often perpe
Externí odkaz:
http://arxiv.org/abs/2410.07274
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