A short trajectory is all you need: A transformer-based model for long-time dissipative quantum dynamics

TL;DR

This paper introduces a transformer-based neural network that accurately predicts long-time quantum system dynamics from short-time data, outperforming classical models and matching state-of-the-art methods.

Contribution

The authors develop a transformer neural network model that effectively predicts long-time dissipative quantum dynamics using only short-time data, demonstrating superior accuracy over classical models.

Findings

Transformer model predicts long-time dynamics accurately across regimes.

Model outperforms recurrent neural networks in accuracy.

Comparable to kernel ridge regression for quantum dynamics.

Abstract

In this communication we demonstrate that a deep artificial neural network based on a transformer architecture with self-attention layers can predict the long-time population dynamics of a quantum system coupled to a dissipative environment provided that the short-time population dynamics of the system is known. The transformer neural network model developed in this work predicts the long-time dynamics of spin-boson model efficiently and very accurately across different regimes, from weak system-bath coupling to strong coupling non-Markovian regimes. Our model is more accurate than classical forecasting models, such as recurrent neural networks and is comparable to the state-of-the-art models for simulating the dynamics of quantum dissipative systems based on kernel ridge regression.