Machine-learning optimized measurements of chaotic dynamical systems via the information bottleneck

• URL: http://arxiv.org/abs/2311.04896v2
• Date: Wed, 20 Mar 2024 01:42:25 GMT
• Title: Machine-learning optimized measurements of chaotic dynamical systems via the information bottleneck
• Authors: Kieran A. Murphy, Dani S. Bassett,
• Abstract summary: A perfect measurement captures all of the information created by the system's evolution with minimal redundancy. Finding an optimal measurement is challenging, and has generally required intimate knowledge of the dynamics in the few cases where it has been done. We employ machine learning to optimize measurement processes that efficiently extract information from trajectory data.
• Score: 4.189643331553922
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deterministic chaos permits a precise notion of a "perfect measurement" as one that, when obtained repeatedly, captures all of the information created by the system's evolution with minimal redundancy. Finding an optimal measurement is challenging, and has generally required intimate knowledge of the dynamics in the few cases where it has been done. We establish an equivalence between a perfect measurement and a variant of the information bottleneck. As a consequence, we can employ machine learning to optimize measurement processes that efficiently extract information from trajectory data. We obtain approximately optimal measurements for multiple chaotic maps and lay the necessary groundwork for efficient information extraction from general time series.

Related papers

• MEXGEN: An Effective and Efficient Information Gain Approximation for Information Gathering Path Planning [3.195234044113248]
  Planning algorithms for autonomous robots need to solve sequential decision making problems under uncertainty. We develop a computationally efficient and effective approximation for the difficult problem of predicting the likely sensor measurements from uncertain belief states. We demonstrate improved performance gains in radio-source tracking and localization problems using extensive simulated and field experiments with a multirotor aerial robot.
  arXiv  Detail & Related papers  (2024-05-04T08:09:16Z)
• Optimization of a Hydrodynamic Computational Reservoir through Evolution [58.720142291102135]
  We interface with a model of a hydrodynamic system, under development by a startup, as a computational reservoir. We optimized the readout times and how inputs are mapped to the wave amplitude or frequency using an evolutionary search algorithm. Applying evolutionary methods to this reservoir system substantially improved separability on an XNOR task, in comparison to implementations with hand-selected parameters.
  arXiv  Detail & Related papers  (2023-04-20T19:15:02Z)
• Information bottleneck theory of high-dimensional regression: relevancy, efficiency and optimality [6.700873164609009]
  Overfitting is a central challenge in machine learning, yet many large neural networks readily achieve zero training loss. We quantify overfitting via residual information, defined as the bits in fitted models that encode noise in training data.
  arXiv  Detail & Related papers  (2022-08-08T00:09:12Z)
• Information-Theoretic Odometry Learning [83.36195426897768]
  We propose a unified information theoretic framework for learning-motivated methods aimed at odometry estimation. The proposed framework provides an elegant tool for performance evaluation and understanding in information-theoretic language.
  arXiv  Detail & Related papers  (2022-03-11T02:37:35Z)
• A dynamic programming algorithm for informative measurements and near-optimal path-planning [0.0]
  An informative measurement is the most efficient way to gain information about an unknown state. We give a first-principles derivation of a general-purpose dynamic programming algorithm that returns a sequence of informative measurements. This algorithm can be used by an autonomous agent or robot to decide where best to measure next.
  arXiv  Detail & Related papers  (2021-09-24T08:40:06Z)
• An Adaptive Framework for Learning Unsupervised Depth Completion [59.17364202590475]
  We present a method to infer a dense depth map from a color image and associated sparse depth measurements. We show that regularization and co-visibility are related via the fitness of the model to data and can be unified into a single framework.
  arXiv  Detail & Related papers  (2021-06-06T02:27:55Z)
• Learning to Measure: Adaptive Informationally Complete Generalized Measurements for Quantum Algorithms [0.0]
  We present an algorithm that optimize informationally complete positive operator-valued measurements (POVMs) on the fly. We show its advantage by improving the efficiency of the variational quantum eigensolver in calculating ground-state energies of molecular Hamiltonians. In addition, the informational completeness of the approach offers a crucial advantage, as the measurement data can be reused to infer other quantities of interest.
  arXiv  Detail & Related papers  (2021-04-01T15:49:05Z)
• Using Data Assimilation to Train a Hybrid Forecast System that Combines Machine-Learning and Knowledge-Based Components [52.77024349608834]
  We consider the problem of data-assisted forecasting of chaotic dynamical systems when the available data is noisy partial measurements. We show that by using partial measurements of the state of the dynamical system, we can train a machine learning model to improve predictions made by an imperfect knowledge-based model.
  arXiv  Detail & Related papers  (2021-02-15T19:56:48Z)
• Estimating informativeness of samples with Smooth Unique Information [108.25192785062367]
  We measure how much a sample informs the final weights and how much it informs the function computed by the weights. We give efficient approximations of these quantities using a linearized network. We apply these measures to several problems, such as dataset summarization.
  arXiv  Detail & Related papers  (2021-01-17T10:29:29Z)
• Gaussianizing the Earth: Multidimensional Information Measures for Earth Data Analysis [9.464720193746395]
  Information theory is an excellent framework for analyzing Earth system data. It allows us to characterize uncertainty and redundancy, and is universally interpretable. We show how information theory measures can be applied in various Earth system data analysis problems.
  arXiv  Detail & Related papers  (2020-10-13T15:30:34Z)
• Evaluating representations by the complexity of learning low-loss predictors [55.94170724668857]
  We consider the problem of evaluating representations of data for use in solving a downstream task. We propose to measure the quality of a representation by the complexity of learning a predictor on top of the representation that achieves low loss on a task of interest.
  arXiv  Detail & Related papers  (2020-09-15T22:06:58Z)

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.