Unsupervised learning of observation functions in state-space models by nonparametric moment methods

• URL: http://arxiv.org/abs/2207.05242v1
• Date: Tue, 12 Jul 2022 00:42:49 GMT
• Title: Unsupervised learning of observation functions in state-space models by nonparametric moment methods
• Authors: Qingci An, Yannis Kevrekidis, Fei Lu, Mauro Maggioni
• Abstract summary: We investigate the unsupervised learning of non-invertible observation functions in nonlinear state-space models. The major challenge comes from the non-invertibility of the observation function and the lack of data pairs between the state and observation.
• Score: 9.405458160620533
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We investigate the unsupervised learning of non-invertible observation functions in nonlinear state-space models. Assuming abundant data of the observation process along with the distribution of the state process, we introduce a nonparametric generalized moment method to estimate the observation function via constrained regression. The major challenge comes from the non-invertibility of the observation function and the lack of data pairs between the state and observation. We address the fundamental issue of identifiability from quadratic loss functionals and show that the function space of identifiability is the closure of a RKHS that is intrinsic to the state process. Numerical results show that the first two moments and temporal correlations, along with upper and lower bounds, can identify functions ranging from piecewise polynomials to smooth functions, leading to convergent estimators. The limitations of this method, such as non-identifiability due to symmetry and stationarity, are also discussed.

Related papers

• On Learning what to Learn: heterogeneous observations of dynamics and establishing (possibly causal) relations among them [4.741643704615452]
  We attempt to learn a function between two (sets of) observables of a physical process. We first decide what the inputs and what the outputs of the desired function are going to be. We construct mappings from a single set of observations of one process to entire level sets of measurements of the process.
  arXiv  Detail & Related papers  (2024-06-10T21:37:36Z)
• Extending Path-Dependent NJ-ODEs to Noisy Observations and a Dependent Observation Framework [6.404122934568861]
  We introduce a new loss function, which allows us to deal with noisy observations and explain why the previously used loss function did not lead to a consistent estimator.
  arXiv  Detail & Related papers  (2023-07-24T22:01:22Z)
• Inference on Strongly Identified Functionals of Weakly Identified Functions [71.42652863687117]
  We study a novel condition for the functional to be strongly identified even when the nuisance function is not. We propose penalized minimax estimators for both the primary and debiasing nuisance functions.
  arXiv  Detail & Related papers  (2022-08-17T13:38:31Z)
• Computationally Efficient PAC RL in POMDPs with Latent Determinism and Conditional Embeddings [97.12538243736705]
  We study reinforcement learning with function approximation for large-scale Partially Observable Decision Processes (POMDPs) Our algorithm provably scales to large-scale POMDPs.
  arXiv  Detail & Related papers  (2022-06-24T05:13:35Z)
• Quadratic pseudospectrum for identifying localized states [68.8204255655161]
  quadratic pseudospectrum is a method for approaching systems with incompatible observables. We derive an important estimate relating the Clifford and quadratic pseudospectra. We prove that the quadratic pseudospectrum is local, and derive bounds on the errors that are incurred by truncating the system in the vicinity of where the pseudospectrum is being calculated.
  arXiv  Detail & Related papers  (2022-04-22T00:57:09Z)
• Reinforcement Learning from Partial Observation: Linear Function Approximation with Provable Sample Efficiency [111.83670279016599]
  We study reinforcement learning for partially observed decision processes (POMDPs) with infinite observation and state spaces. We make the first attempt at partial observability and function approximation for a class of POMDPs with a linear structure.
  arXiv  Detail & Related papers  (2022-04-20T21:15:38Z)
• An Indirect Rate-Distortion Characterization for Semantic Sources: General Model and the Case of Gaussian Observation [83.93224401261068]
  Source model is motivated by the recent surge of interest in the semantic aspect of information. intrinsic state corresponds to the semantic feature of the source, which in general is not observable. Rate-distortion function is the semantic rate-distortion function of the source.
  arXiv  Detail & Related papers  (2022-01-29T02:14:24Z)
• Causal Discovery from Conditionally Stationary Time Series [18.645887749731923]
  State-Dependent Causal Inference (SDCI) is able to recover the underlying causal dependencies, provably with fully-observed states and empirically with hidden states. improved results over non-causal RNNs on modeling NBA player movements demonstrate the potential of our method.
  arXiv  Detail & Related papers  (2021-10-12T18:12:57Z)
• OR-Net: Pointwise Relational Inference for Data Completion under Partial Observation [51.083573770706636]
  This work uses relational inference to fill in the incomplete data. We propose Omni-Relational Network (OR-Net) to model the pointwise relativity in two aspects.
  arXiv  Detail & Related papers  (2021-05-02T06:05:54Z)
• Learning interaction kernels in stochastic systems of interacting particles from multiple trajectories [13.3638879601361]
  We consider systems of interacting particles or agents, with dynamics determined by an interaction kernel. We introduce a nonparametric inference approach to this inverse problem, based on a regularized maximum likelihood estimator. We show that a coercivity condition enables us to control the condition number of this problem and prove the consistency of our estimator.
  arXiv  Detail & Related papers  (2020-07-30T01:28:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.