paper-with-me

홈 › Papers

Learning low-dimensional state embeddings and metastable clusters from time series data

2019-06-01 · NeurIPS 2019 12 · Yifan Sun, Yaqi Duan, Hao Gong, Mengdi Wang

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.

📄 PDF Abstract BibTeX arXiv:1906.00302

Code (0)

등록된 구현이 없습니다.

Tasks

ClusteringTime SeriesTime Series Analysis

Similar Papers 제목 키워드 기반

Variational embedding of protein folding simulations using gaussian mixture variational autoencoders

2021-08-27 · Mahdi Ghorbani, Samarjeet Prasad, Jeffery B. Klauda, Bernard R. Brooks

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 Folding

Metastable Dynamics of Chain-of-Thought Reasoning: Provable Benefits of Search, RL and Distillation

2025-02-02 · Juno Kim, Denny Wu, Jason Lee, Taiji Suzuki

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 Methods

Deep Generative Markov State Models

2018-05-19 · NeurIPS 2018 12 · Hao Wu, Andreas Mardt, Luca Pasquali, Frank Noe

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 Analysisvalid

Discrete distributions are learnable from metastable samples

2024-10-17 · Abhijith Jayakumar, Andrey Y. Lokhov, Sidhant Misra, Marc Vuffray

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

2019-04-18 · Andreas Bittracher, Stefan Klus, Boumediene Hamzi, Péter Koltai 외

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