arXiv research

The paper provides a non-asymptotic error bound for linear system identification under nonlinear policies.

The paper proves that linearization along trajectories preserves flatness in discrete-time systems.

Study online control of unknown time-varying systems with negative and positive results.

Estimates time-varying parameters from two OLS estimates.

New algorithm reduces control error in systems with changing dynamics.

We present a windowed technique to learn parsimonious time-varying autoregressive models from multivariate timeseries. This unsupervised method uncovers interpretable spatiotemporal structure in data via non-smooth and non-convex optimization. In each time window, we assume the data follow a linear model parameterized …

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

Flexible nonlinear Hawkes processes for time-varying systems.

Improved robust latent variable estimation for neural dynamics.

We establish a connection between trend filtering and system identification which results in a family of new identification methods for linear, time-varying (LTV) dynamical models based on convex optimization. We demonstrate how the design of the cost function promotes a model with either a continuous change in dynamic…

Extends tracking guarantees for time-varying variational inequalities.

Extends double linear policy with time-varying weights and proves robust positive expectation.

Adaptive ML learns complex time-varying systems without new data.

This paper introduces a linear state-space model with time-varying dynamics. The time dependency is obtained by forming the state dynamics matrix as a time-varying linear combination of a set of matrices. The time dependency of the weights in the linear combination is modelled by another linear Gaussian dynamical model…

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

This study proposes an approach based on a perturbation technique to construct global solutions to dynamic stochastic general equilibrium models (DSGE). The main idea is to expand a solution in a series of powers of a small parameter scaling the uncertainty in the economy around a solution to the deterministic model, i…

Geometric framework for dynamic feedback linearization of control systems with symmetry.

A new framework improves volatility forecasting for financial markets.

Motivated by their broad applications in reinforcement learning, we study the linear two-time-scale stochastic approximation, an iterative method using two different step sizes for finding the solutions of a system of two equations. Our main focus is to characterize the finite-time complexity of this method under time-…

A new method estimates time-varying parameters in earth system models using offline and online data assimilation.

This paper proposes a formal approach to online learning and planning for agents operating in a priori unknown, time-varying environments. The proposed method computes the maximally likely model of the environment, given the observations about the environment made by an agent earlier in the system run and assuming know…

New method learns time-varying home field advantage in football.

DIGing-SGLD improves SGLD for scalable Bayesian learning in dynamic networks.

A new algorithm optimizes time-varying functions with non-constant evaluation times.

A new method for steering large agent populations efficiently.

This paper develops a non-Bayesian methodology to analyze the time-varying structure of international linkages and market efficiency in G7 countries. We consider a non-Bayesian time-varying vector autoregressive (TV-VAR) model, and apply it to estimate the joint degree of market efficiency in the sense of Fama (1970, 1…

New algorithms optimize actions under time-varying constraints without projecting.

A new approach optimizes weights in DLP for better risk-adjusted performance.

We simplify Bayesian filtering by framing it as optimization, making it practical for high-dimensional systems.

New algorithm reduces regret in CBs with time-varying models.

The paper analyzes equity market dynamics and optimal portfolios using time-varying optimization.

Meta-learning method for estimating time-varying mHealth intervention effects.

Most of the existing methods for sparse signal recovery assume a static system: the unknown signal is a finite-length vector for which a fixed set of linear measurements and a sparse representation basis are available and an L1-norm minimization program is solved for the reconstruction. However, the same representation…

Balanced Neural ODEs combine VAEs and Neural ODEs for efficient time series modeling.

In this note, we present a version of the Thompson sampling algorithm for the problem of online linear generalization with full information (i.e., the experts setting), studied by Kalai and Vempala, 2005. The algorithm uses a Gaussian prior and time-varying Gaussian likelihoods, and we show that it essentially reduces …

In this paper, we propose an acceleration scheme for online memory-limited PCA methods. Our scheme converges to the first $k>1$ eigenvectors in a single data pass. We provide empirical convergence results of our scheme based on the spiked covariance model. Our scheme does not require any predefined parameters such as t…

New model predicts time-varying interactions in complex systems.

Optimal control of stochastic nonlinear dynamical systems is a major challenge in the domain of robot learning. Given the intractability of the global control problem, state-of-the-art algorithms focus on approximate sequential optimization techniques, that heavily rely on heuristics for regularization in order to achi…

New method calibrates probabilistic linear solver for online coverage guarantees.

In this work the system of agents is applied to establish a model of the nonlinear distributed signal processing. The evolution of the system of the agents - by the prediction time scale diversified trend followers, has been studied for the stochastic time-varying environments represented by the real currency-exchange …

In this work, we study the problem of aggregating a finite number of predictors for nonstationary sub-linear processes. We provide oracle inequalities relying essentially on three ingredients: (1) a uniform bound of the $\ell^1$ norm of the time varying sub-linear coefficients, (2) a Lipschitz assumption on the predict…

RNNs compute by warping neural representations over time.

Stochastic networks are a plausible representation of the relational information among entities in dynamic systems such as living cells or social communities. While there is a rich literature in estimating a static or temporally invariant network from observation data, little has been done toward estimating time-varyin…

The paper tackles revenue management with time-varying demand using posterior sampling.

Proposes a model to estimate treatment effects in complex multiagent systems over time.

We show LLMs can be locally linear, enabling better control of activations.

Proposes a new model to measure trade impact and information content in fluctuating markets.

Bayesian method detects change points in time series data.