| DOI | Resolve DOI: https://doi.org/10.1109/QCE60285.2024.10262 |
|---|
| Author | Search for: Gonzalez, Sebastian; Search for: Jia, Hao; Search for: Toledo-Marin, J. Quetzalcoatl; Search for: Hoque, Sehmimul; Search for: Abhishek, Abhishek; Search for: Lu, Ian; Search for: Sogutlu, Deniz; Search for: Anderson, Soren; Search for: Gay, Colin; Search for: Paquet, Eric1ORCID identifier: https://orcid.org/0000-0001-6515-2556; Search for: Melko, Roger; Search for: Fox, Geoffrey; Search for: Swiatlowski, Maximilian; Search for: Fedorko, Wojciech |
|---|
| Affiliation | - National Research Council of Canada. Digital Technologies
|
|---|
| Funder | Search for: Natural Sciences and Engineering Research Council; Search for: Ontario through the Ministry of Research, Innovation and Science |
|---|
| Format | Text, Article |
|---|
| Conference | 2024 IEEE International Conference on Quantum Computing and Engineering (QCE24), September 15-20, 2024, Montréal, Québec, Canada |
|---|
| Subject | generative AI; quantum annealers; calorimeters; high energy physics; restricted Boltzmann machines |
|---|
| Abstract | As we approach the High Luminosity Large Hadron Collider (HL-LHC) set to begin collisions by the end of this decade, it is clear that the computational demands of traditional collision simulations have become untenably high. Current methods, relying heavily on first-principles Monte Carlo simulations for event showers in calorimeters, are estimated to require millions of CPU-years annually, a demand that far exceeds current capabilities. This bottleneck presents a unique opportunity for breakthroughs in computational physics through the integration of generative AI with quantum computing technologies. We propose a quantum-assisted deep generative model. In particular, we combine a variational autoencoder (VAE) with a restricted Boltzmann machine (RBM) embedded in its latent space as a prior. The RBM in latent space provides further expressiveness compared to legacy VAE where the prior is a fixed Gaussian distribution. By crafting the RBM couplings, we leverage DWave's quantum annealer to significantly speed up the shower sampling time. By combining classical and quantum computing, this framework sets a path towards utilizing large-scale quantum simulations as priors in deep generative models and demonstrate their ability to generate high-quality synthetic data for the HLLHC experiments. |
|---|
| Publication date | 2025-01-10 |
|---|
| Publisher | IEEE |
|---|
| In | |
|---|
| Language | English |
|---|
| Peer reviewed | Yes |
|---|
| Export citation | Export as RIS |
|---|
| Report a correction | Report a correction (opens in a new tab) |
|---|
| Record identifier | 02a831a2-4a09-48b4-8f1e-37628a8e4b20 |
|---|
| Record created | 2025-01-16 |
|---|
| Record modified | 2025-01-16 |
|---|
