Learning low-dimensional state embeddings and metastable clusters from time series data
This paper studies how to find compact state embeddings from high-dimensional Markov state trajectories, where the transition kernel has a small intrinsic rank. In the spirit of diffusion map, we propose an efficient method for learning a low-dimensional state embedding and capturing the process's dynamics. This idea also leads to a kernel reshaping method for more accurate nonparametric estimation of the transition function. State embedding can be used to cluster states into metastable sets, thereby identifying the slow dynamics. Sharp statistical error bounds and misclassification rate are proved. Experiment on a simulated dynamical system shows that the state clustering method indeed reveals metastable structures. We also experiment with time series generated by layers of a Deep-Q-Network when playing an Atari game. The embedding method identifies game states to be similar if they share similar future events, even though their raw data are far different.
Code (0)
등록된 구현이 없습니다.
Tasks
ClusteringTime SeriesTime Series AnalysisSimilar Papers 제목 키워드 기반
Variational embedding of protein folding simulations using gaussian mixture variational autoencoders
Conformational sampling of biomolecules using molecular dynamics simulations often produces large amount of high dimensional data that makes it difficult to interpret using conventional analysis techniques. Dimensionalit…
Dimensionality ReductionProtein FoldingMetastable Dynamics of Chain-of-Thought Reasoning: Provable Benefits of Search, RL and Distillation
A key paradigm to improve the reasoning capabilities of large language models (LLMs) is to allocate more inference-time compute to search against a verifier or reward model. This process can then be utilized to refine th…
Policy Gradient MethodsDeep Generative Markov State Models
We propose a deep generative Markov State Model (DeepGenMSM) learning framework for inference of metastable dynamical systems and prediction of trajectories. After unsupervised training on time series data, the model con…
Time SeriesTime Series AnalysisvalidDiscrete distributions are learnable from metastable samples
Physically motivated stochastic dynamics are often used to sample from high-dimensional distributions. However such dynamics often get stuck in specific regions of their state space and mix very slowly to the desired sta…
Dimensionality Reduction of Complex Metastable Systems via Kernel Embeddings of Transition Manifolds
We present a novel kernel-based machine learning algorithm for identifying the low-dimensional geometry of the effective dynamics of high-dimensional multiscale stochastic systems. Recently, the authors developed a mathe…
Dimensionality Reduction