中文
相关论文

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

200 篇论文

In a Networked Dynamical System (NDS), each node is a system whose dynamics are coupled with the dynamics of neighboring nodes. The global dynamics naturally builds on this network of couplings and it is often excited by a noise input with…

机器学习 · 计算机科学 2023-12-19 Augusto Santos , Diogo Rente , Rui Seabra , José M. F. Moura

We propose a system identification method, Non-Markovian Optimization-based Modeling for Approximate Dynamics with Spatially-homogeneous memory (NOMADS), for identifying linear dynamical systems from a set of multi-dimensional time-series…

最优化与控制 · 数学 2026-01-27 Ryoji Anzaki , Kazuhiro Sato

Recent work has focused on data-driven learning of the evolution of unknown systems via deep neural networks (DNNs), with the goal of conducting long term prediction of the dynamics of the unknown system. In many real-world applications,…

机器学习 · 计算机科学 2022-06-07 Victor Churchill , Dongbin Xiu

We present a numerical method for learning unknown nonautonomous stochastic dynamical system, i.e., stochastic system subject to time dependent excitation or control signals. Our basic assumption is that the governing equations for the…

机器学习 · 计算机科学 2025-03-04 Yuan Chen , Dongbin Xiu

Modern learning systems increasingly interact with data that evolve over time and depend on hidden internal state. We ask a basic question: when is such a dynamical system learnable from observations alone? This paper proposes a research…

机器学习 · 计算机科学 2025-12-23 Elad Hazan , Shai Shalev Shwartz , Nathan Srebro

Mathematical models for complex systems are often accompanied with uncertainties. The goal of this paper is to extract a stochastic differential equation governing model with observation on stationary probability distributions. We develop a…

动力系统 · 数学 2023-04-05 Xiaoli Chen , Hui Wang , Jinqiao Duan

We study the problem of PAC learning $\gamma$-margin halfspaces in the presence of Massart noise. Without computational considerations, the sample complexity of this learning problem is known to be $\widetilde{\Theta}(1/(\gamma^2…

机器学习 · 计算机科学 2025-01-17 Ilias Diakonikolas , Nikos Zarifis

Advection-dominated dynamical systems, characterized by partial differential equations, are found in applications ranging from weather forecasting to engineering design where accuracy and robustness are crucial. There has been significant…

计算物理 · 物理学 2020-06-29 Romit Maulik , Bethany Lusch , Prasanna Balaprakash

We study the problem of agnostically learning halfspaces which is defined by a fixed but unknown distribution $\mathcal{D}$ on $\mathbb{Q}^n\times \{\pm 1\}$. We define $\mathrm{Err}_{\mathrm{HALF}}(\mathcal{D})$ as the least error of a…

计算复杂性 · 计算机科学 2016-03-15 Amit Daniely

We consider the problem of minimizing a convex function that is evolving according to unknown and possibly stochastic dynamics, which may depend jointly on time and on the decision variable itself. Such problems abound in the machine…

最优化与控制 · 数学 2023-05-30 Joshua Cutler , Dmitriy Drusvyatskiy , Zaid Harchaoui

In reinforcement learning (RL), temporal difference (TD) errors are widely adopted for optimizing value and policy functions. However, since the TD error is defined by a bootstrap method, its computation tends to be noisy and destabilize…

机器学习 · 计算机科学 2026-04-03 Taisuke Kobayashi

Learning continuous-time stochastic dynamics is a fundamental and essential problem in modeling sporadic time series, whose observations are irregular and sparse in both time and dimension. For a given system whose latent states and…

机器学习 · 计算机科学 2021-04-30 Yingru Liu , Yucheng Xing , Xuewen Yang , Xin Wang , Jing Shi , Di Jin , Zhaoyue Chen

Discrete-time fractional-order dynamical systems (DT-FODS) have found innumerable applications in the context of modeling spatiotemporal behaviors associated with long-term memory. Applications include neurophysiological signals such as…

最优化与控制 · 数学 2021-10-05 Sarthak Chatterjee , Sérgio Pequito

This paper analyzes a new regularized learning scheme for high dimensional partially linear support vector machine. The proposed approach consists of an empirical risk and the Lasso-type penalty for linear part, as well as the standard…

统计理论 · 数学 2020-06-08 Yifan Xia , Yongchao Hou , Shaogao Lv

The main objective of the paper is to study the long-time behavior of general discrete dynamics driven by an ergodic stationary Gaussian noise. In our main result, we prove existence and uniqueness of the invariant distribution and exhibit…

概率论 · 数学 2018-11-14 Maylis Varvenne

We study the problem of \textit{safe control of linear dynamical systems corrupted with non-stochastic noise}, and provide an algorithm that guarantees (i) zero constraint violation of convex time-varying constraints, and (ii) bounded…

系统与控制 · 电气工程与系统科学 2023-08-25 Hongyu Zhou , Vasileios Tzoumas

We present a mathematical and computational framework for the problem of learning a dynamical system from noisy observations of a few trajectories and subject to side information. Side information is any knowledge we might have about the…

最优化与控制 · 数学 2022-01-19 Amir Ali Ahmadi , Bachir El Khadir

Many robotic systems are underactuated, meaning not all degrees of freedom can be directly controlled due to lack of actuators, input constraints, or state-dependent actuation. This property, compounded by modeling uncertainties and…

系统与控制 · 电气工程与系统科学 2025-10-10 Daniel M. Cherenson , Dimitra Panagou

This paper studies the stochastic optimal control problem for systems with unknown dynamics. First, an open-loop deterministic trajectory optimization problem is solved without knowing the explicit form of the dynamical system. Next, a…

系统与控制 · 计算机科学 2017-05-30 Dan Yu , Mohammadhussein Rafieisakhaei , Suman Chakravorty

In the context of high-dimensional linear regression models, we propose an algorithm of exact support recovery in the setting of noisy compressed sensing where all entries of the design matrix are independent and identically distributed…

统计理论 · 数学 2019-10-23 Mohamed Ndaoud , Alexandre B. Tsybakov