Learning Low-dimensional Latent Dynamics from High-dimensional Observations: Non-asymptotics and Lower Bounds
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 low-dimensional model parameters. Our algorithm enjoys a sample complexity guarantee of order $\tilde{\mathcal{O}}(n/\epsilon^2)$, where $n$ is the observation dimension. We further establish a fundamental lower bound indicating this complexity bound is optimal up to logarithmic factors and dimension-independent constants. We show that this inevitable linear factor of $n$ is due to the learning error of the observer's column space in the presence of high-dimensional noises. Extending our results, we consider a meta-learning problem inspired by various real-world applications, where the observer column space can be collectively learned from datasets of multiple LTI systems. An end-to-end algorithm is then proposed, facilitating learning LTI systems from a meta-dataset which breaks the sample complexity lower bound in certain scenarios.
Code (0)
등록된 구현이 없습니다.
Tasks
Meta-LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Beta DVBF: Learning State-Space Models for Control from High Dimensional Observations
Learning a model of dynamics from high-dimensional images can be a core ingredient for success in many applications across different domains, especially in sequential decision making. However, currently prevailing method…
Decision MakingSequential Decision MakingState Space ModelsPredictive Coding for Locally-Linear Control
High-dimensional observations and unknown dynamics are major challenges when applying optimal control to many real-world decision making tasks. The Learning Controllable Embedding (LCE) framework addresses these challeng…
Decision MakingDecoderLD-EnSF: Synergizing Latent Dynamics with Ensemble Score Filters for Fast Data Assimilation with Sparse Observations
Data assimilation techniques are crucial for correcting the trajectory when modeling complex physical systems. A recently developed data assimilation method, Latent Ensemble Score Filter (Latent-EnSF), has shown great pr…
Non-Markovian Predictive Coding For Planning In Latent Space
High-dimensional observations are a major challenge in the application of model-based reinforcement learning (MBRL) to real-world environments. In order to handle high-dimensional sensory inputs, existing MBRL approaches…
Model-based Reinforcement LearningRepresentation LearningHeteroscedastic Uncertainty for Robust Generative Latent Dynamics
Learning or identifying dynamics from a sequence of high-dimensional observations is a difficult challenge in many domains, including reinforcement learning and control. The problem has recently been studied from a gener…