Koopman Learning with Episodic Memory

• URL: http://arxiv.org/abs/2311.12615v2
• Date: Fri, 18 Oct 2024 20:18:47 GMT
• Title: Koopman Learning with Episodic Memory
• Authors: William T. Redman, Dean Huang, Maria Fonoberova, Igor Mezić,
• Abstract summary: We equip Koopman methods - developed for predicting non-autonomous time-series - with an episodic memory mechanism. We find that a basic implementation of Koopman learning with episodic memory leads to significant improvements in prediction on synthetic and real-world data.
• Score: 9.841748637412596
• License:
• Abstract: Koopman operator theory has found significant success in learning models of complex, real-world dynamical systems, enabling prediction and control. The greater interpretability and lower computational costs of these models, compared to traditional machine learning methodologies, make Koopman learning an especially appealing approach. Despite this, little work has been performed on endowing Koopman learning with the ability to leverage its own failures. To address this, we equip Koopman methods - developed for predicting non-autonomous time-series - with an episodic memory mechanism, enabling global recall of (or attention to) periods in time where similar dynamics previously occurred. We find that a basic implementation of Koopman learning with episodic memory leads to significant improvements in prediction on synthetic and real-world data. Our framework has considerable potential for expansion, allowing for future advances, and opens exciting new directions for Koopman learning.

Related papers

• Deep Learning Through A Telescoping Lens: A Simple Model Provides Empirical Insights On Grokking, Gradient Boosting & Beyond [61.18736646013446]
  In pursuit of a deeper understanding of its surprising behaviors, we investigate the utility of a simple yet accurate model of a trained neural network. Across three case studies, we illustrate how it can be applied to derive new empirical insights on a diverse range of prominent phenomena.
  arXiv  Detail & Related papers  (2024-10-31T22:54:34Z)
• A Unified Framework for Neural Computation and Learning Over Time [56.44910327178975]
  Hamiltonian Learning is a novel unified framework for learning with neural networks "over time" It is based on differential equations that: (i) can be integrated without the need of external software solvers; (ii) generalize the well-established notion of gradient-based learning in feed-forward and recurrent networks; (iii) open to novel perspectives.
  arXiv  Detail & Related papers  (2024-09-18T14:57:13Z)
• Koopman Invertible Autoencoder: Leveraging Forward and Backward Dynamics for Temporal Modeling [13.38194491846739]
  We propose a novel machine learning model based on Koopman operator theory, which we call Koopman Invertible Autoencoders (KIA) KIA captures the inherent characteristic of the system by modeling both forward and backward dynamics in the infinite-dimensional Hilbert space. This enables us to efficiently learn low-dimensional representations, resulting in more accurate predictions of long-term system behavior.
  arXiv  Detail & Related papers  (2023-09-19T03:42:55Z)
• Koopa: Learning Non-stationary Time Series Dynamics with Koopman Predictors [85.22004745984253]
  Real-world time series are characterized by intrinsic non-stationarity that poses a principal challenge for deep forecasting models. We tackle non-stationary time series with modern Koopman theory that fundamentally considers the underlying time-variant dynamics. We propose Koopa as a novel Koopman forecaster composed of stackable blocks that learn hierarchical dynamics.
  arXiv  Detail & Related papers  (2023-05-30T07:40:27Z)
• Koopman Kernel Regression [6.116741319526748]
  We show that Koopman operator theory offers a beneficial paradigm for characterizing forecasts via linear time-invariant (LTI) ODEs. We derive a universal Koopman-invariant kernel reproducing Hilbert space (RKHS) that solely spans transformations into LTI dynamical systems. Our experiments demonstrate superior forecasting performance compared to Koopman operator and sequential data predictors.
  arXiv  Detail & Related papers  (2023-05-25T16:22:22Z)
• Understanding Self-Predictive Learning for Reinforcement Learning [61.62067048348786]
  We study the learning dynamics of self-predictive learning for reinforcement learning. We propose a novel self-predictive algorithm that learns two representations simultaneously.
  arXiv  Detail & Related papers  (2022-12-06T20:43:37Z)
• DLKoopman: A deep learning software package for Koopman theory [0.0]
  We present DLKoopman, a software package for Koopman theory. It uses deep learning to learn an encoding of a nonlinear dynamical system into a linear space, while simultaneously learning the linear dynamics. DLKoopman is available on the Python Package Index (PyPI) as 'dlkoopman'
  arXiv  Detail & Related papers  (2022-11-15T18:45:51Z)
• A Koopman Approach to Understanding Sequence Neural Models [2.8783296093434148]
  We introduce a new approach to understanding trained sequence neural models: the Koopman Analysis of Neural Networks (KANN) method. Motivated by the relation between time-series models and self-maps, we compute approximate Koopman operators that encode well the latent dynamics. Our results extend across tasks and architectures as we demonstrate for the copy problem, ECG classification and sentiment analysis tasks.
  arXiv  Detail & Related papers  (2021-02-15T20:05:11Z)
• Forecasting Sequential Data using Consistent Koopman Autoencoders [52.209416711500005]
  A new class of physics-based methods related to Koopman theory has been introduced, offering an alternative for processing nonlinear dynamical systems. We propose a novel Consistent Koopman Autoencoder model which, unlike the majority of existing work, leverages the forward and backward dynamics. Key to our approach is a new analysis which explores the interplay between consistent dynamics and their associated Koopman operators.
  arXiv  Detail & Related papers  (2020-03-04T18:24:30Z)
• Value-driven Hindsight Modelling [68.658900923595]
  Value estimation is a critical component of the reinforcement learning (RL) paradigm. Model learning can make use of the rich transition structure present in sequences of observations, but this approach is usually not sensitive to the reward function. We develop an approach for representation learning in RL that sits in between these two extremes. This provides tractable prediction targets that are directly relevant for a task, and can thus accelerate learning the value function.
  arXiv  Detail & Related papers  (2020-02-19T18:10:20Z)

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.