Reduced Precision Strategies for Deep Learning: A High Energy Physics Generative Adversarial Network Use Case

Rehm, Florian; Vallecorsa, S.; Saletore, Vikram A.; Pabst, Hans; Chaibi, Adel; Codreanu, Valeriu; Borras, K.; Krücker, D.

doi:10.5220/0010245002510258

Cited by 9 publications

(5 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the simplified calorimeter use case, this is more than sufficient. For comparison, in a previous classical reduced precision ML research in [29], it is demonstrated that already 256 discrete energy levels are sufficient for correctly reproducing the full-size calorimeter shower image. In this reduced precision research, the parameters of the neural network are quantized from a larger format (floating point 32) down to a smaller number format (integer 8).…”

Section: Model Descriptionmentioning

confidence: 90%

Precise image generation on current noisy quantum computing devices

Rehm,

Vallecorsa,

Borras

et al. 2023

Quantum Sci. Technol.

Self Cite

View full text Add to dashboard Cite

The Quantum Angle Generator (QAG) is a new full Quantum Machine Learning model designed to generate accurate images on current Noise Intermediate Scale (NISQ) Quantum devices. Variational quantum circuits form the core of the QAG model, and various circuit architectures are evaluated. In combination with the so-called MERA-upsampling architecture, the QAG model achieves excellent results, which are analyzed and evaluated in detail. To our knowledge, this is the first time that a quantum model has achieved such accurate results. To explore the robustness of the model to noise, an extensive quantum noise study is performed. In this paper, it is demonstrated that the model trained on a physical quantum device learns the noise characteristics of the hardware and generates outstanding results. It is verified that even a quantum hardware machine calibration change during training of up to 8% can be well tolerated. For demonstration, the model is employed in indispensable simulations in high energy physics required to measure particle energies and, ultimately, to discover unknown particles at the Large Hadron Collider at CERN.

show abstract

Section: Model Descriptionmentioning

confidence: 90%

Precise image generation on current noisy quantum computing devices

Rehm,

Vallecorsa,

Borras

et al. 2023

Quantum Sci. Technol.

Self Cite

View full text Add to dashboard Cite

show abstract

“…The goal of this paper is to study the statistical amplification of deep generative models, focusing on interpolation from the smoothness inductive bias, for detector simulations as a realistic and highly relevant application. Fast surrogate models for detector simulations have been developed [13][14][15][16][17][18][19][20][21][22][23][24][25] and improved [26][27][28][29][30][31][32][33][34][35][36][37][38][39][40] to the level that they are ready to be used in the upcoming LHC runs. In fact, the ATLAS Collaboration has already integrated a Generative Adversarial Network (GAN) into its fast calorimeter simulation and will use it to generate over a billion events [41,42].…”

Section: Jinst 17 P09028mentioning

confidence: 99%

Calomplification — the power of generative calorimeter models

et al. 2022

View full text Add to dashboard Cite

Motivated by the high computational costs of classical simulations, machine-learned generative models can be extremely useful in particle physics and elsewhere. They become especially attractive when surrogate models can efficiently learn the underlying distribution, such that a generated sample outperforms a training sample of limited size. This kind of GANplification has been observed for simple Gaussian models. We show the same effect for a physics simulation, specifically photon showers in an electromagnetic calorimeter.

show abstract

“…Weather forecasting centres in both the UK (Gilham, 2018) and Switzerland (Rudisuhli et al, 2014) have also explored the benefits of reduced‐precision arithmetic. Beyond numerical weather forecasting, reduced‐precision methods are now deployed routinely in neural network models (Hopkins et al, 2020; Gupta and Ranga, 2021; Rehm et al, 2021; Noune et al, 2022), which motivates the development of dedicated CPU and accelerator hardware and architectures (TensorFlow, 2020; Training With Mixed Precision, 2021) that can take advantage of reduced‐precision formats. These advances in hardware may in turn also be exploited by the numerical weather modelling community.…”

Section: Introductionmentioning

confidence: 99%

Climate‐change modelling at reduced floating‐point precision with stochastic rounding

Kimpson

Paxton

Chantry

et al. 2023

Quart J Royal Meteoro Soc

View full text Add to dashboard Cite

Reduced‐precision floating‐point arithmetic is now deployed routinely in numerical weather forecasting over short timescales. However, the applicability of these reduced‐precision techniques to longer‐timescale climate simulations—especially those that seek to describe a dynamical, changing climate—remains unclear. We investigate this question by deploying a global atmospheric, coarse‐resolution model known as Simplified Parameterizations PrimitivE Equation DYnamics (SPEEDY) to simulate a changing climate system subject to increased CO2$$ {\mathrm{CO}}_2 $$ concentrations, over a 100‐year timescale. Whilst double precision is typically the operational standard for climate modelling, we find that reduced‐precision solutions are sufficiently accurate. Rounding the floating‐point numbers stochastically, rather than using the more common “round‐to‐nearest” technique, improves the performance of the reduced‐precision solutions notably. Over 100 years, the mean bias error (MBE) in the global mean surface temperature (precipitation) relative to the double‐precision solution is +1.8 prefix×10prefix−2$$ \times 1{0}^{-2} $$ K (prefix−8prefix×10prefix−4$$ -8\times 1{0}^{-4} $$ mm·$$ \cdotp $$(6 hr)prefix−1$$ {}^{-1} $$) when integrating numerically at half precision (10 significant bits) with stochastic rounding. By examining the resultant climatic distributions that arise after 100 years, the difference in the expected value of the global surface temperature relative to the double‐precision solution is ≤5prefix×10prefix−3$$ \le 5\times 1{0}^{-3} $$ K and that for precipitation is 8prefix×10prefix−4$$ 8\times 1{0}^{-4} $$ mm·$$ \cdotp $$(6 hr)prefix−1$$ {}^{-1} $$. Whilst further research is necessary to extended these results to more complex and higher‐resolution models, they indicate that reduced‐precision techniques and stochastic rounding could be suitable for the next generation of climate models and motivate the use of low‐precision hardware to this end.

show abstract

Reduced Precision Strategies for Deep Learning: A High Energy Physics Generative Adversarial Network Use Case

Cited by 9 publications

References 12 publications

Precise image generation on current noisy quantum computing devices

Precise image generation on current noisy quantum computing devices

Calomplification — the power of generative calorimeter models

Climate‐change modelling at reduced floating‐point precision with stochastic rounding

Contact Info

Product

Resources

About