arXiv research

The paper tackles joint learning of linear systems, improving accuracy with pooled data.

Paper derives an error bound for stochastic LTI systems.

A method for learning with autoregressive chain-of-thoughts.

This paper focuses on using the first curvature $κ(t)$ of trajectory to describe the stability of linear time-invariant system. We extend the results for two and three-dimensional systems [Y. Wang, H. Sun, Y. Song et al., arXiv:1808.00290] to $n$-dimensional systems. We prove that for a system $\dot{r}(t)=Ar(t)$, (i) i…

This paper proposes a new approach to describe the stability of linear time-invariant systems via the torsion $τ(t)$ of the state trajectory. For a system $\dot{r}(t)=Ar(t)$ where $A$ is invertible, we show that (1) if there exists a measurable set $E_1$ with positive Lebesgue measure, such that $r(0)\in E_1$ implies t…

New model stabilizes asynchronous LTI systems, independent of synchronous stability.

We prove that stochastic gradient descent efficiently converges to the global optimizer of the maximum likelihood objective of an unknown linear time-invariant dynamical system from a sequence of noisy observations generated by the system. Even though the objective function is non-convex, we provide polynomial running …

Study reveals how travel times on cylindrical boundaries can identify spacetime structure.

Evolution of planar curves under a nonlocal geometric equation is investigated. It models the simultaneous contraction and growth of carbonate particles called ooids in geosciences. Using classical ODE results and a bijective mapping we demonstrate that the steady parameters associated with the physical environment det…

New method learns time-invariant rewards from demonstrations.

We provide a brief tutorial on the use of concentration inequalities as they apply to system identification of state-space parameters of linear time invariant systems, with a focus on the fully observed setting. We draw upon tools from the theories of large-deviations and self-normalized martingales, and provide both d…

This work represents an application of constant mean curvature graphs (as solutions of the mean curvature PDE) to non-linear non-Darcy flows in porous media. It relates time invariant pressure distribution graphs to graphs of constant mean curvature surfaces. This differential geometric interpretation provides an impor…

AR model forecasts partially observed dynamical time series by estimating evolution function and imputing missing variables.

Paper tests if beta coefficients in AMF model are consistent over time.

We study the problem of controlling linear time-invariant systems with known noisy dynamics and adversarially chosen quadratic losses. We present the first efficient online learning algorithms in this setting that guarantee $O(\sqrt{T})$ regret under mild assumptions, where $T$ is the time horizon. Our algorithms rely …

In this work, we propose a robust approach to design distributed controllers for unknown-but-sparse linear and time-invariant systems. By leveraging modern techniques in distributed controller synthesis and structured linear inverse problems as applied to system identification, we show that near-optimal distributed con…

dynoGP uses deep Gaussian processes for dynamic system identification.

Study shows exponential sample complexity for stabilizing certain linear systems.

We build a simple diagnostic criterion for approximate factor structure in large cross-sectional equity datasets. Given a model for asset returns with observable factors, the criterion checks whether the error terms are weakly cross-sectionally correlated or share at least one unobservable common factor. It only requir…

New measure EC assesses node contributions in nonlinear, time-varying systems.

We consider the problem of learning a realization for a linear time-invariant (LTI) dynamical system from input/output data. Given a single input/output trajectory, we provide finite time analysis for learning the system's Markov parameters, from which a balanced realization is obtained using the classical Ho-Kalman al…

New insights into spectral statistics of sample covariance matrix for stable linear systems.

New test uncovers causal links in rare event dynamics.

SPAQL improves RL by adaptively partitioning state-action space and learning a time-invariant policy.

Safety filter for unknown discrete-time systems with learned models and noise covariance.

Over the past few years, we developed a mathematically rigorous method to study the dynamical processes associated to nonlinear Forchheimer flows for slightly compressible fluids. We have proved the existence of a geometric transformation which relates constant mean curvature surfaces and time-invariant pressure distri…

The OLS estimator optimally identifies stable linear systems with a finite number of samples.

Time-invariant linear dynamical system arises in many real-world applications,and its usefulness is widely acknowledged. A practical limitation with this model is that its latent dimension that has a large impact on the model capability needs to be manually specified. It can be demonstrated that a lower-order model cla…

Solves parameter non-identifiability in Bayesian LTI system identification.

Paper tackles temporal overfitting in wind power curve modeling.

In this paper we propose a new identification scheme for Hammerstein systems, which are dynamic systems consisting of a static nonlinearity and a linear time-invariant dynamic system in cascade. We assume that the nonlinear function can be described as a linear combination of $p$ basis functions. We reconstruct the $p$…

The paper develops robust tests for detecting independence in synchronous stochastic systems with finite sample guarantees.

The Kalman filter is the most powerful tool for estimation of the states of a linear Gaussian system. In addition, using this method, an expectation maximization algorithm can be used to estimate the parameters of the model. However, this algorithm cannot function in real time. Thus, we propose a new method that can be…

Gaussian processes for dynamical systems with Koopman equivariance.

The Expectation-Maximization (EM) algorithm is one of the most popular methods used to solve the problem of parametric distribution-based clustering in unsupervised learning. In this paper, we propose to analyze a generalized EM (GEM) algorithm in the context of Gaussian mixture models, where the maximization step in t…

Recurrent and convolutional neural networks are the most common architectures used for time series forecasting in deep learning literature. These networks use parameter sharing by repeating a set of fixed architectures with fixed parameters over time or space. The result is that the overall architecture is time-invaria…

Ensemble++ uses shared-factor ensembles to scale Thompson Sampling for linear and nonlinear bandits.

Improved stability analysis of neural network systems using Zames-Falb multipliers.

We consider the problem of discrete-time signal denoising, focusing on a specific family of non-linear convolution-type estimators. Each such estimator is associated with a time-invariant filter which is obtained adaptively, by solving a certain convex optimization problem. Adaptive convolution-type estimators were dem…

Iterative method learns unknown constraints for MPC control.

Complex frequency generalizes eigenvalues in LTI systems.

BP fails to find sparsest solution for structured matrices.

Algorithm learns linear systems from partial observations with near-optimal rate.

Treatment effects can be estimated from observational data as the difference in potential outcomes. In this paper, we address the challenge of estimating the potential outcome when treatment-dose levels can vary continuously over time. Further, the outcome variable may not be measured at a regular frequency. Our propos…

Paper derives PAC-Bayesian bounds for LTI systems learning from empirical data.

Study cost-driven state representation learning for control from partial observations.

Unified Bayesian framework for LTV system identification using neural networks and Gaussian Processes.

New algorithm optimizes linear system estimation from single trajectory.