Learning theory for inferring interaction kernels in second-order interacting agent systems
نویسندگان
چکیده
Abstract Modeling the complex interactions of systems particles or agents is a fundamental problem across sciences, from physics and biology, to economics social sciences. In this work, we consider second-order, heterogeneous, multivariable models interacting particles, within simple environments. We describe nonparametric inference framework efficiently estimate latent interaction kernels which drive these dynamical systems. develop learning theory establishes strong consistency optimal min–max rates convergence for estimators, as well provably accurate predicted trajectories. The only depends on intrinsic dimension interactions, typically much smaller than ambient dimension. Our arguments are based coercivity condition ensures that can be estimated in stable fashion. numerical algorithm presented build estimators parallelizable, performs high-dimensional problems, its performance tested variety
منابع مشابه
On leaderless and leader-following consensus for interacting clusters of second-order multi-agent systems
This paper investigates the group consensus phenomenon for multiple interacting clusters of doubleintegrator agents in the presence of both cooperative and competitive inter-cluster couplings under two different frameworks, viz., the framework that all agents share the same position and velocity interaction topology and the framework that the position and velocity topologies are modeled by tota...
متن کاملSynchronization Theory for Forced Oscillations in Second-Order Systems ~
We consider differential equations of the form ~ + ~f(x, ~ ) + x = Eu, where E > 0 is supposed to be small. For piecewise continuous controls u(t), satisfying lu( t ) l -1 , we present sulIicient conditions for the existence of 2¢r-periodic solutions with a given amplitude. We present a method for determining the limiting behavior of controls fi, for which the equation has a 27r-periodic soluti...
متن کاملWaveform Design using Second Order Cone Programming in Radar Systems
Transmit waveform design is one of the most important problems in active sensing and communication systems. This problem, due to the complexity and non-convexity, has been always the main topic of many papers for the decades. However, still an optimal solution which guarantees a global minimum for this multi-variable optimization problem is not found. In this paper, we propose an attracting met...
متن کاملA Pure First Order Representation for Undamped Second Order Descriptor Systems
The aim of this paper is to analyze the undamped second order descriptor systems to show the possibility of transform an undamped second order descriptor system to a pure first order descriptor system ,on different ways, while stating some of its benefits. Meanwhile we will introduce pure first order systems and undamped second order systems and indicate that under some assumptions every undamp...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Sampling theory, signal processing, and data analysis
سال: 2023
ISSN: ['2730-5724', '1530-6429', '2730-5716']
DOI: https://doi.org/10.1007/s43670-023-00055-9