Solving the quantum many-body problem with artificial neural networks
Problem
The exponential complexity of the many-body wave function makes describing interacting quantum systems computationally intractable.
Why it matters
The many-body problem is a central, long-standing challenge of quantum physics.
What the AI did
Quantum states are represented variationally as artificial neural networks with variable hidden neurons; a reinforcement-learning scheme finds ground states and describes unitary time evolution.
Results
High accuracy describing prototypical interacting spin models in one and two dimensions; ground states and time evolution demonstrated.
Impact
Shows machine learning can make some interacting quantum systems computationally tractable.
Record
| Venue | Science |
|---|---|
| Published | 2017 |
| Work type | article |
| Authors | Giuseppe Carleo, Matthias Troyer |
| Citations | 2,205 (OpenAlex, at import time) |
| References | 57 |
| Model or method | artificial neural networks (variational quantum state representation) |
| Organization | not stated in source |
| Primary source | https://doi.org/10.1126/science.aag2302 |
| Open access | green |
| Keywords | quantum many-body, neural networks, ground state, reinforcement learning, variational methods |
Importance rating
significant — thousands to millions affected
Many-body problem is described as originating from exponential complexity of the wave function—a central challenge of quantum physics; ML makes some interacting systems tractable, a foundational scientific advance, though demonstrated only on prototypical spin models.
More in Physics & Astronomy
| # | Paper | Year | Citations | Importance |
|---|---|---|---|---|
| 1 | Magnetic control of tokamak plasmas through deep reinforcement learning | 2022 | 739 |
7
|
| 2 | Learning high-accuracy error decoding for quantum processors | 2024 | 90 |
7
|
| 3 | Optimizing Quantum Error Correction Codes with Reinforcement Learning | 2019 | 158 |
7
|
| 4 | Machine-learning-assisted correction of correlated qubit errors in a topological code | 2018 | 141 |
7
|
| 5 | Quantum Error Correction with Quantum Autoencoders | 2023 | 36 |
7
|