Tame-Narvaez, Karla Maria [Fermilab]

DOE OSTI2025

Simulation-Based Inference for Neutrino Interaction Model Parameter Tuning

High-energy physics experiments studying neutrinos rely heavily on simulations of their interactions with atomic nuclei. Limitations in the theoretical understanding of these interactions typically necessitate ad hoc tuning of simulation model parameters to data. Traditional tuning methods for neutrino experiments have largely relied on simple algorithms for numerical optimization. While adequate for the modest goals of initial efforts, the complexity of future neutrino tuning campaigns is expected to increase substantially, and new approaches will be needed to make progress. In this paper, we examine the application of simulation-based inference (SBI) to the neutrino interaction model tuning for the first time. Using a previous tuning study performed by the MicroBooNE experiment as a test case, we find that our SBI algorithm can correctly infer the tuned parameter values when confronted with a mock data set generated according to the MicroBooNE procedure. This initial proof-of-principle illustrates a promising new technique for next-generation simulation tuning campaigns for the neutrino experimental community.

Tame-Narvaez, Karla Maria [Fermilab]↗

DOE OSTI2025

wa-hls4ml: A Benchmark and Surrogate Models for hls4ml Resource and Latency Estimation

As machine learning (ML) is increasingly implemented in hardware to address real-time challenges in scientific applications, the development of advanced toolchains has significantly reduced the time required to iterate on various designs. These advancements have solved major obstacles, but also exposed new challenges. For example, processes that were not previously considered bottlenecks, such as hardware synthesis, are becoming limiting factors in the rapid iteration of designs. To mitigate these emerging constraints, multipleefforts have been undertaken to develop an ML-based surrogate model that estimates resource usage of synthesized ML accelerator architectures. We introduce wa-hls4ml, a benchmark for ML accelerator resource and latency estimation, and its corresponding initial dataset of over 680 000 fully connected and convolutional neural networks, all synthesized using hls4ml and targeting Xilinx FPGAs. The benchmark evaluates the performance of resource and latency predictors against several common ML model architectures, primarily originating from scientific domains, as exemplar models, and the average performance across a subset of the dataset. Additionally, we introduce GNN- and transformer-based surrogate models that predict latency and resources for ML accelerators. We present the architecture and performance of the models and find that the models generally predict latency and resources for the 75% percentile within several percent of the synthesized resources on the synthetic test dataset.

Hawks, Benjamin G. [Fermilab]↗