Choose Your Diffusion: Efficient and flexible ways to accelerate the diffusion model in fast high energy physics simulation (2401.13162v2)
Abstract: The diffusion model has demonstrated promising results in image generation, recently becoming mainstream and representing a notable advancement for many generative modeling tasks. Prior applications of the diffusion model for both fast event and detector simulation in high energy physics have shown exceptional performance, providing a viable solution to generate sufficient statistics within a constrained computational budget in preparation for the High Luminosity LHC. However, many of these applications suffer from slow generation with large sampling steps and face challenges in finding the optimal balance between sample quality and speed. The study focuses on the latest benchmark developments in efficient ODE/SDE-based samplers, schedulers, and fast convergence training techniques. We test on the public CaloChallenge and JetNet datasets with the designs implemented on the existing architecture, the performance of the generated classes surpass previous models, achieving significant speedup via various evaluation metrics.
- L. Evans and P. Bryant, LHC Machine, Journal of Instrumentation 3(08), S08001 (2008), 10.1088/1748-0221/3/08/S08001.
- G. Aad et al., The ATLAS Experiment at the CERN Large Hadron Collider, JINST 3, S08003 (2008), 10.1088/1748-0221/3/08/S08003.
- S. Chatrchyan et al., The CMS Experiment at the CERN LHC, JINST 3, S08004 (2008), 10.1088/1748-0221/3/08/S08004.
- S. Agostinelli et al., GEANT4–a simulation toolkit, Nucl. Instrum. Meth. A 506, 250 (2003), 10.1016/S0168-9002(03)01368-8.
- High Luminosity Large Hadron Collider HL-LHC, 10.5170/CERN-2015-005.1 (2015).
- M. Paganini, L. de Oliveira and B. Nachman, CaloGAN: Simulating 3D high energy particle showers in multilayer electromagnetic calorimeters with generative adversarial networks, Physical Review D 97(1) (2018), 10.1103/physrevd.97.014021.
- C. Krause and D. Shih, Fast and accurate simulations of calorimeter showers with normalizing flows, Physical Review D 107(11) (2023), 10.1103/physrevd.107.113003.
- R. Zhang, AtlFast3, the ATLAS fast simulation tool in Run3 (2023).
- Hadrons, better, faster, stronger (2021), 2112.09709.
- Supercalo: Calorimeter shower super-resolution (2024), 2308.11700.
- M. F. Giannelli and R. Zhang, Caloshowergan, a generative adversarial networks model for fast calorimeter shower simulation (2023), 2309.06515.
- Caloqvae : Simulating high-energy particle-calorimeter interactions using hybrid quantum-classical generative models (2023), 2312.03179.
- Flow matching beyond kinematics: Generating jets with particle-id and trajectory displacement information (2023), 2312.00123.
- Calomplification — the power of generative calorimeter models, Journal of Instrumentation 17(09), P09028 (2022), 10.1088/1748-0221/17/09/p09028.
- Deeptreegan: Fast generation of high dimensional point clouds (2023), 2311.12616.
- K. Dohi, Variational autoencoders for jet simulation (2020), 2009.04842.
- C. Krause and D. Shih, Caloflow ii: Even faster and still accurate generation of calorimeter showers with normalizing flows (2023), 2110.11377.
- Anomaly detection with flow-based fast calorimeter simulators (2023), 2312.11618.
- V. Mikuni and B. Nachman, Score-based generative models for calorimeter shower simulation, Physical Review D 106(9) (2022), 10.1103/physrevd.106.092009.
- O. Amram and K. Pedro, Denoising diffusion models with geometry adaptation for high fidelity calorimeter simulation (2023), 2308.03876.
- Caloclouds: Fast geometry-independent highly-granular calorimeter simulation (2023), 2305.04847.
- Pc-jedi: Diffusion for particle cloud generation in high energy physics (2023), 2303.05376.
- Epic-ly fast particle cloud generation with flow-matching and diffusion (2023), 2310.00049.
- V. Mikuni and B. Nachman, Caloscore v2: Single-shot calorimeter shower simulation with diffusion models (2023), 2308.03847.
- T. Salimans and J. Ho, Progressive distillation for fast sampling of diffusion models (2022), 2202.00512.
- Caloclouds ii: Ultra-fast geometry-independent highly-granular calorimeter simulation (2023), 2309.05704.
- Consistency models (2023), 2303.01469.
- Pc-droid: Faster diffusion and improved quality for particle cloud generation (2023), 2307.06836.
- High-resolution image synthesis with latent diffusion models (2022), 2112.10752.
- Dreambooth: Fine tuning text-to-image diffusion models for subject-driven generation (2023), 2208.12242.
- L. Zhang, A. Rao and M. Agrawala, Adding conditional control to text-to-image diffusion models (2023), 2302.05543.
- Text-to-image diffusion models can be easily backdoored through multimodal data poisoning (2023), 2305.04175.
- J. Song, C. Meng and S. Ermon, Denoising diffusion implicit models (2022), 2010.02502.
- Fast calorimeter simulation challenge 2022 (2022).
- Particle cloud generation with message passing generative adversarial networks (2022), 2106.11535.
- Deep unsupervised learning using nonequilibrium thermodynamics (2015), 1503.03585.
- Diffusion models: A comprehensive survey of methods and applications (2023), 2209.00796.
- Diffusion models, image super-resolution and everything: A survey (2024), 2401.00736.
- J. Ho, A. Jain and P. Abbeel, Denoising diffusion probabilistic models (2020), 2006.11239.
- A. Nichol and P. Dhariwal, Improved denoising diffusion probabilistic models (2021), 2102.09672.
- Score-based generative modeling through stochastic differential equations (2021), 2011.13456.
- Elucidating the design space of diffusion-based generative models (2022), 2206.00364.
- Dpm-solver: A fast ode solver for diffusion probabilistic model sampling in around 10 steps (2022), 2206.00927.
- Restart sampling for improving generative processes (2023), 2306.14878.
- Dpm-solver++: Fast solver for guided sampling of diffusion probabilistic models (2023), 2211.01095.
- Unipc: A unified predictor-corrector framework for fast sampling of diffusion models (2023), 2302.04867.
- The anti-ktjet clustering algorithm, Journal of High Energy Physics 2008(04), 063–063 (2008), 10.1088/1126-6708/2008/04/063.
- P. Dhariwal and A. Nichol, Diffusion models beat gans on image synthesis (2021), 2105.05233.
- On distillation of guided diffusion models (2023), 2210.03142.
- Video diffusion models (2022), 2204.03458.
- Efficient diffusion training via min-snr weighting strategy (2023), 2303.09556.
- Evaluating generative models in high energy physics, Physical Review D 107(7) (2023), 10.1103/physrevd.107.076017.
- Y. Song and P. Dhariwal, Improved techniques for training consistency models (2023), 2310.14189.
- H. Qu and L. Gouskos, Jet tagging via particle clouds, Physical Review D 101(5) (2020), 10.1103/physrevd.101.056019.