中文
相关论文

相关论文: Improved rates for prediction and identification o…

200 篇论文

We study the problem of learning general (i.e., not necessarily homogeneous) halfspaces with Random Classification Noise under the Gaussian distribution. We establish nearly-matching algorithmic and Statistical Query (SQ) lower bound…

机器学习 · 计算机科学 2023-07-18 Ilias Diakonikolas , Jelena Diakonikolas , Daniel M. Kane , Puqian Wang , Nikos Zarifis

A variety of complex biological, natural and man-made systems exhibit non-Markovian dynamics that can be modeled through fractional order differential equations, yet, we lack sample comlexity aware system identification strategies. Towards…

系统与控制 · 电气工程与系统科学 2025-06-23 Xiaole Zhang , Vijay Gupta , Paul Bogdan

This paper addresses identification of sparse linear and noise-driven continuous-time state-space systems, i.e., the right-hand sides in the dynamical equations depend only on a subset of the states. The key assumption in this study, is…

系统与控制 · 计算机科学 2018-04-18 Zuogong Yue , Johan Thunberg , Lennart Ljung , Jorge Goncalves

In this paper, we analyze the finite sample complexity of stochastic system identification using modern tools from machine learning and statistics. An unknown discrete-time linear system evolves over time under Gaussian noise without…

机器学习 · 计算机科学 2019-03-22 Anastasios Tsiamis , George J. Pappas

We consider the problem of learning stabilizable systems governed by nonlinear state equation $h_{t+1}=\phi(h_t,u_t;\theta)+w_t$. Here $\theta$ is the unknown system dynamics, $h_t $ is the state, $u_t$ is the input and $w_t$ is the…

机器学习 · 计算机科学 2021-11-22 Yahya Sattar , Samet Oymak

System identification is of special interest in science and engineering. This article is concerned with a system identification problem arising in stochastic dynamic systems, where the aim is to estimate the parameters of a system along…

统计方法学 · 统计学 2022-01-27 Christos Merkatas , Simo Särkkä

We consider the problem of learning a realization of a partially observed bilinear dynamical system (BLDS) from noisy input-output data. Given a single trajectory of input-output samples, we provide a finite time analysis for learning the…

机器学习 · 计算机科学 2025-10-23 Yahya Sattar , Yassir Jedra , Maryam Fazel , Sarah Dean

We present a numerical method to learn an accurate predictive model for an unknown stochastic dynamical system from its trajectory data. The method seeks to approximate the unknown flow map of the underlying system. It employs the idea of…

机器学习 · 计算机科学 2024-12-24 Zhongshu Xu , Yuan Chen , Qifan Chen , Dongbin Xiu

We consider the problem of learning a realization of a partially observed dynamical system with linear state transitions and bilinear observations. Under very mild assumptions on the process and measurement noises, we provide a finite time…

机器学习 · 计算机科学 2024-09-26 Yahya Sattar , Yassir Jedra , Sarah Dean

We present an efficient and practical (polynomial time) algorithm for online prediction in unknown and partially observed linear dynamical systems (LDS) under stochastic noise. When the system parameters are known, the optimal linear…

机器学习 · 计算机科学 2020-10-13 Paria Rashidinejad , Jiantao Jiao , Stuart Russell

Dynamical systems are used to model a variety of phenomena in which the bifurcation structure is a fundamental characteristic. Here we propose a statistical machine-learning approach to derive lowdimensional models that automatically…

定量方法 · 定量生物学 2015-06-11 Yohei Kondo , Kunihiko Kaneko , Shuji Ishihara

We introduce and test a general machine-learning-based technique for the inference of short term causal dependence between state variables of an unknown dynamical system from time series measurements of its state variables. Our technique…

适应与自组织系统 · 物理学 2020-12-18 Amitava Banerjee , Jaideep Pathak , Rajarshi Roy , Juan G. Restrepo , Edward Ott

We consider the problem of controlling a possibly unknown linear dynamical system with adversarial perturbations, adversarially chosen convex loss functions, and partially observed states, known as non-stochastic control. We introduce a…

机器学习 · 计算机科学 2020-06-26 Max Simchowitz , Karan Singh , Elad Hazan

The reconstruction and inference of stochastic dynamical systems from data is a fundamental task in inverse problems and statistical learning. While surrogate modeling advances computational methods to approximate these dynamics, standard…

最优化与控制 · 数学 2026-04-14 Nicole Tianjiao Yang

We study the fundamental problem of learning the parameters of a high-dimensional Gaussian in the presence of noise -- where an $\varepsilon$-fraction of our samples were chosen by an adversary. We give robust estimators that achieve…

数据结构与算法 · 计算机科学 2017-11-07 Ilias Diakonikolas , Gautam Kamath , Daniel M. Kane , Jerry Li , Ankur Moitra , Alistair Stewart

This paper addresses the problem of identifying sparse linear time-invariant (LTI) systems from a single sample trajectory generated by the system dynamics. We introduce a Lasso-like estimator for the parameters of the system, taking into…

系统与控制 · 计算机科学 2019-04-23 Salar Fattahi , Nikolai Matni , Somayeh Sojoudi

This paper leverages recent advances in high derivatives reconstruction from noisy-time series and sparse multivariate polynomial identification in order to improve the process of parsimoniously identifying, from a small amount of data,…

系统与控制 · 电气工程与系统科学 2025-09-23 Mazen Alamir

We develop an approach to learn an interpretable semi-parametric model of a latent continuous-time stochastic dynamical system, assuming noisy high-dimensional outputs sampled at uneven times. The dynamics are described by a nonlinear…

机器学习 · 统计学 2019-02-13 Lea Duncker , Gergo Bohner , Julien Boussard , Maneesh Sahani

Learning how complex dynamical systems evolve over time is a key challenge in system identification. For safety critical systems, it is often crucial that the learned model is guaranteed to converge to some equilibrium point. To this end,…

机器学习 · 计算机科学 2021-12-13 Andreas Schlaginhaufen , Philippe Wenk , Andreas Krause , Florian Dörfler

The identification of a linear system model from data has wide applications in control theory. The existing work that provides finite sample guarantees for linear system identification typically uses data from a single long system…

机器学习 · 统计学 2025-05-09 Lei Xin , Baike She , Qi Dou , George Chiu , Shreyas Sundaram