← Search

Shahriar Talebi

2 accepted papers

2024

Learning Low-dimensional Latent Dynamics from High-dimensional Observations: Non-asymptotics and Lower Bounds

ICML 2024poster

In this paper, we focus on learning a linear time-invariant (LTI) model with low-dimensional latent variables but high-dimensional observations. We provide an algorithm that recovers the high-dimensional features, i.e. column space of the observer, embeds the data into low dimensions and learns the…

Cited by 2SourcePDFScholar
2023

Data-driven Optimal Filtering for Linear Systems with Unknown Noise Covariances

NeurIPS 2023poster

This paper examines learning the optimal filtering policy, known as the Kalman gain, for a linear system with unknown noise covariance matrices using noisy output data. The learning problem is formulated as a stochastic policy optimiza- tion problem, aiming to minimize the output prediction error. T…