As Simple as Possible but No Simpler: Optimizing the Performance of Neural Net Emulators for Galaxy SED Fitting

Elijah P. Mathews; Joel Leja; Joshua S. Speagle; Benjamin D. Johnson; Justus Gibson; Erica J. Nelson; Katherine A. Suess; Sandro Tacchella; Katherine E. Whitaker; Bingjie Wang

arXiv · 2306.16442

As Simple as Possible but No Simpler: Optimizing the Performance of Neural Net Emulators for Galaxy SED Fitting

Elijah P. Mathews·Joel Leja·Joshua S. Speagle·Benjamin D. Johnson·Justus Gibson·Erica J. Nelson·Katherine A. Suess·Sandro Tacchella·Katherine E. Whitaker·Bingjie Wang

View original source ↗Read source document ↗Export metadata ↓

Abstract

Artificial neural network emulators have been demonstrated to be a very computationally efficient method to rapidly generate galaxy spectral energy distributions (SEDs), for parameter inference or otherwise. Using a highly flexible and fast mathematical structure, they can learn the nontrivial relationship between input galaxy parameters and output observables. However, they do so imperfectly, and small errors in flux prediction can yield large differences in recovered parameters. In this work, we investigate the relationship between an emulator's execution time, uncertainties, correlated errors, and ability to recover accurate posteriors. We show that emulators can recover consistent results to traditional fits, with precision of $25\!-\!40\%$ in posterior medians for stellar mass, stellar metallicity, star formation rate, and stellar age. We find that emulation uncertainties scale with an emulator's width $N$ as $\propto N^{-1}$ while execution time scales as $\propto N^2$, resulting in an inherent tradeoff between execution time and emulation uncertainties. We also find that emulators with uncertainties smaller than observational uncertaities are able to recover accurate posteriors for most parameters without a significant increase in catastrophic outliers. Furthermore, we demonstrate that small architectures can produce flux residuals that have significant correlations, which can create dangerous systematic errors in colors. Finally, we show that the distributions chosen for generating training sets can have a large effect on emulators' ability to accurately fit rare objects. Selecting the optimal architecture and training set for an emulator will minimize the computational requirements for fitting near-future large-scale galaxy surveys.

Explore related subjects

astro-ph.IM

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

Elijah P. Mathews, Joel Leja, Joshua S. Speagle, Benjamin D. Johnson, Justus Gibson, Erica J. Nelson, Katherine A. Suess, Sandro Tacchella, Katherine E. Whitaker, Bingjie Wang. 2023-06-28. As Simple as Possible but No Simpler: Optimizing the Performance of Neural Net Emulators for Galaxy SED Fitting. https://arxiv.org/abs/2306.16442

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Radial Pulsations in Polaris: A Secondary Science Application of Cherenkov Telescopes via Intensity Interferometry

Ground-based Cherenkov telescopes, which are typically inoperative during moonlit nights for gamma-ray observations, offer a valuable opportunity during this time for secondary scientific applications through Intensity Interferometry (II). Recent developments and observations suggest that implementing II instrumentation on existing and planned Imaging Atmospheric Cherenkov Telescopes (IACTs) can significantly advance optical stellar measurements. Motivated by the resurgence of II efforts over the past two decades, this work presents simulations demonstrating the estimation of stellar parameters for a radially pulsating star, such as Polaris, using either a single telescope or multiple telescopes. For single-telescope simulations, we assume that the photon pixels in the camera are mapped onto four distinct regions of the aperture, generating multiple baselines and enabling enhanced observational plane coverage. These results highlight the potential of Cherenkov telescopes in India for high-resolution optical astronomy during otherwise inoperative periods and offer promising insights into the characterization of bright stellar objects with unprecedented precision.

astro-ph.IM↗

arXiv2026

Parallel adaptive reweighting importance sampling for Bayesian astrophysics

Efficient sampling from high-dimensional, multi-modal posteriors is a central challenge in Bayesian inference across the physical sciences. Gravitational-wave (GW) astronomy, where likelihood evaluations are computationally expensive and posteriors are complex, is one application motivating this work. Popular families of methods like Markov-chain Monte Carlo, nested sampling, and importance sampling all rely on proposal distributions to guide exploration. Because prior knowledge of the target is often limited, practitioners can adopt adaptive proposals that iteratively refine themselves using information gained from previously drawn samples. Traditional adaptive strategies, however, struggle in high-dimensional multi-modal settings: complex, non-linear correlations are hard to capture, and hyperparameters typically require tedious, problem-specific tuning. To address these issues, we introduce Parallel Adaptive Reweighting Importance Sampling (PARIS; descriptively, ``seed sampling''). PARIS models its proposal as a Gaussian mixture whose component centers are the existing samples and whose component weights match the current importance weights. New draws from the proposal therefore concentrate around high-weight regions, while candidate points in unexplored areas receive intentionally inflated weights. As the algorithm continuously reweights all samples up to the latest proposal, any initial over-weighting self-corrects once additional neighbor samples are collected. To enable rapid reweighting, we present an efficient update scheme and evaluate PARIS on illustrative toy problems and more realistic gravitational-wave parameter estimation tasks. PARIS achieves accurate posterior reconstruction and evidence estimation with substantially fewer function evaluations than competing approaches, highlighting its promise for widespread use in astrophysical data analysis.

astro-ph.IM↗

arXiv2026

Ising noise filter: physics-informed filtering for particle detectors

We present the Ising noise filter, a highly portable, graph-based pre-filtering algorithm for early-stage background suppression in particle accelerators and astrophysical detectors. Standard noise rejection methods relying on track fitting suffer from severe combinatorial explosion. Our method bypasses this by mapping individual detector hits to a network of binary spins and minimizing an energy functional. The interaction kernels are physics-informed, tailored to the underlying physics and geometry of the experiment. We demonstrate the efficacy of this approach in two distinct experimental regimes. Applied to the Baikal-GVD neutrino telescope the filter yields fast, standard-quality noise rejection with 96.8% recall for astrophysical neutrinos. For the SPD detector at the NICA collider the filter attains recall of 97% on a toy Monte Carlo sample. Furthermore, when combined with a Peterson--Hopfield network for track finding, our physics-informed coupling improves the TrackML score from 0.5 to 0.95.

astro-ph.IM↗