RydbergGPT

TL;DR

RydbergGPT is a transformer-based model that predicts measurement outcomes of Rydberg atom quantum computers, demonstrating generalization near phase transitions and providing a foundation for future quantum data modeling.

Contribution

It introduces RydbergGPT, a novel transformer architecture tailored for quantum measurement prediction, with demonstrated generalization and open-source availability.

Findings

Effective in predicting measurement outcomes near quantum phase transitions

Capable of generalizing to unseen Hamiltonian parameters

Trained efficiently on a single GPU for benchmark purposes

Abstract

We introduce a generative pretained transformer (GPT) designed to learn the measurement outcomes of a neutral atom array quantum computer. Based on a vanilla transformer, our encoder-decoder architecture takes as input the interacting Hamiltonian, and outputs an autoregressive sequence of qubit measurement probabilities. Its performance is studied in the vicinity of a quantum phase transition in Rydberg atoms in a square lattice array. We explore the ability of the architecture to generalize, by producing groundstate measurements for Hamiltonian parameters not seen in the training set. We focus on examples of physical observables obtained from inference on three different models, trained in fixed compute time on a single NVIDIA A100 GPU. These can act as benchmarks for the scaling of larger RydbergGPT models in the future. Finally, we provide RydbergGPT open source, to aid in the development of foundation models based off of a wide variety of quantum computer interactions and data sets in the future.