Transformer Quantum State: A Multi-Purpose Model for Quantum Many-Body Problems

TL;DR

The paper introduces the transformer quantum state (TQS), a versatile machine learning model inspired by transformer-based language models, capable of addressing various quantum many-body problems within a single framework.

Contribution

It presents TQS as a novel, general-purpose quantum model that can generate phase diagrams, predict experimental measurements, and transfer knowledge to unseen systems.

Findings

TQS can generate entire phase diagrams.

TQS accurately predicts field strengths from measurements.

TQS adapts easily to new quantum tasks with fine-tuning.

Abstract

Inspired by the advancements in large language models based on transformers, we introduce the transformer quantum state (TQS): a versatile machine learning model for quantum many-body problems. In sharp contrast to Hamiltonian/task specific models, TQS can generate the entire phase diagram, predict field strengths with experimental measurements, and transfer such a knowledge to new systems it has never been trained on before, all within a single model. With specific tasks, fine-tuning the TQS produces accurate results with small computational cost. Versatile by design, TQS can be easily adapted to new tasks, thereby pointing towards a general-purpose model for various challenging quantum problems.