Learning to simulate high energy particle collisions from unlabeled data
importance 5/10
ai assisted
Particle physics theoretical and experimental studies high-energy physics stage: research
Problem
Simulating how theoretical particle physics models map to experimental collision data is extremely computationally expensive.
Why it matters
Slow, costly simulations bottleneck statistical inference in high-energy physics experiments.
What the AI did
OTUS, an unsupervised machine-learning simulator, trains a probabilistic autoencoder on unlabeled data to transform theoretical models directly into predicted experimental data.
Results
not stated in source
Impact
Abstract claims a fast predictive simulator, but no quantitative speed or accuracy figures are given.
Record
| Venue | Scientific Reports |
|---|---|
| Published | 2022 |
| Work type | article |
| Authors | J. Howard, Stephan Mandt, Daniel Whiteson, Yibo Yang |
| Citations | 40 (OpenAlex, at import time) |
| References | 75 |
| Model or method | OTUS (probabilistic autoencoder) |
| Organization | not stated in source |
| Primary source | https://doi.org/10.1038/s41598-022-10966-7 |
| Open access | gold |
| Keywords | particle physics, simulation, optimal transport, autoencoder, unsupervised learning |
Importance rating
5
real but narrower advance
Abstract says numerical simulations map theory to data at great computational cost, bottlenecking statistical inference; proof-of-principle on two particle physics examples, no quantified scale.
More in Physics & Astronomy
| # | Paper | Year | Citations | Importance |
|---|---|---|---|---|
| 1 | Magnetic control of tokamak plasmas through deep reinforcement learning | 2022 | 739 |
7
|
| 2 | Solving the quantum many-body problem with artificial neural networks | 2017 | 2,205 |
7
|
| 3 | Learning high-accuracy error decoding for quantum processors | 2024 | 90 |
7
|
| 4 | Optimizing Quantum Error Correction Codes with Reinforcement Learning | 2019 | 158 |
7
|
| 5 | Machine-learning-assisted correction of correlated qubit errors in a topological code | 2018 | 141 |
7
|