Probabilistic Data-Driven Modelling of Astrophysical Transients: The Neural Process Family for Ultrafast and Class-Agnostic Light Curve Reconstruction with NightLANP

• URL: http://arxiv.org/abs/2605.27527v2
• Date: Mon, 01 Jun 2026 16:48:58 GMT
• Title: Probabilistic Data-Driven Modelling of Astrophysical Transients: The Neural Process Family for Ultrafast and Class-Agnostic Light Curve Reconstruction with NightLANP
• Abstract summary: We introduce the neural process family for light curve reconstruction.<n>We show that even an unoptimized, out-of-the-box Attentive Neural Process consistently outperforms all benchmarks.<n>Our model interpolates all bands simultaneously in microseconds, over four orders of magnitude faster than the next-best neural benchmark.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Astrophysical observations from Earth are subject to weather, environmental, and scientific constraints that lead to sparse, irregular light curves. On the eve of the Vera C. Rubin Observatory Legacy Survey of Space and Time, its dataset offers unprecedented opportunities for transient science. Yet a key challenge remains its cadence, sparse and irregular across six bands, limiting inference. Interpolation helps mitigate this, with Gaussian Processes the standard, but they struggle with cross-band correlations, require a priori kernel specification, and must be fit to each light curve individually, hence scaling poorly. Here, we introduce the neural process family for light curve reconstruction, combining the probabilistic framework of Gaussian Processes with the scalability of deep learning. By meta-learning on diverse simulated transients, Attentive Neural Processes shift the bulk of computation to training, enabling rapid, amortized inference with a class-agnostic model. Evaluated on realistic Rubin cadences across 15 transient classes, we show that even an unoptimized, out-of-the-box Attentive Neural Process consistently outperforms all benchmarks -- a suite of Gaussian Processes and neural networks -- on every tested metric, spanning regression quality, astrophysical feature recovery, and probabilistic calibration. Our model interpolates all bands simultaneously in microseconds, over four orders of magnitude faster than the next-best neural benchmark and five faster than Gaussian Processes, demonstrating the potential of neural processes for the nightly Rubin alert stream. Attentive Neural Processes avoid the overconfidence of standard neural networks and the underconfidence of Gaussian Processes, delivering sharp, well-calibrated uncertainties. This work establishes the neural process family as a scalable, probabilistic foundation for real-time transient science in the Rubin era.

Related papers

• Flexible Spectral-Normalized Neural Gaussian Process for Dynamic Aperture Prediction [0.0]
  We propose an empirical Bayes method for automatically tuning the hyperparameters of a flexible, heteroscedastic Spectral-normalized Neural Gaussian Process.<n>We demonstrate the practical impact of our method on the task of estimating the dynamic aperture in circular particle accelerators.<n>Our results show that the proposed method achieves competitive predictive performance and well-calibrated uncertainty estimates at much lower computational cost than state-of-the-art approaches.
  arXiv  Detail & Related papers  (2026-09-08T11:55:43Z)
• Neural Symbollic Regression Using Deep Learning and Sparse Modelling [0.0]
  Symbolic Regression seeks to find succinct mathematical expressions that represent fundamental relationships within data.<n>Traditional methods like Genetic Programming face challenges with scalability and are highly sensitive to noise.<n>We present a Neural Symbolic Regression framework that treats neural networks as functional preconditioners for symbolic discovery.
  arXiv  Detail & Related papers  (2026-09-01T11:46:28Z)
• From Atoms to Entropy: Optimal Noise Allocation for Diffusion Training in the Convex Regime [52.459513910242485]
  We develop a general statistical framework for studying optimal noise-level allocation in diffusion training.<n>We show that the optimized training schedule admits an atomic minimizer, concentrated on finitely many noise levels.<n>We then evaluate the entropic schedule in larger-scale experiments, where full schedule optimization is currently intractable.
  arXiv  Detail & Related papers  (2026-07-10T20:59:06Z)
• On Neural Scaling Laws for Weather Emulation through Continual Training [76.70310203875866]
  We study neural scaling in Scientific Machine Learning, focusing on models for weather forecasting.<n>To analyze scaling behavior in as simple a setting as possible, we adopt a minimal, scalable, general-purpose Swin Transformer architecture.<n>We show that models trained in this minimalist way follow predictable scaling trends and even outperform standard cosine learning rate schedules.
  arXiv  Detail & Related papers  (2026-03-26T17:37:25Z)
• Bayesian Interpolating Neural Network (B-INN): a scalable and reliable Bayesian model for large-scale physical systems [0.8593015118377854]
  This paper proposes a scalable and reliable Bayesian surrogate model, termed the Bayesian Interpolating Neural Network (B-INN)<n>B-INN combines high-order theory with tensor decomposition and alternating direction algorithm to enable effective dimensionality reduction without compromising predictive accuracy.<n> Numerical experiments demonstrate that B-INNs can be from 20 times to 10,000 times faster with a robust uncertainty estimation.
  arXiv  Detail & Related papers  (2026-01-30T11:38:42Z)
• Spectral Convolutional Conditional Neural Processes [4.52069311861025]
  Conditional Neural Processes (CNPs) constitute a family of probabilistic models that harness the flexibility of neural networks to parameterize processes. We propose Spectral Convolutional Conditional Neural Processes (SConvCNPs), a new addition to the NPs family that allows for more efficient representation of functions in the frequency domain.
  arXiv  Detail & Related papers  (2024-04-19T21:13:18Z)
• Speed Limits for Deep Learning [67.69149326107103]
  Recent advancement in thermodynamics allows bounding the speed at which one can go from the initial weight distribution to the final distribution of the fully trained network. We provide analytical expressions for these speed limits for linear and linearizable neural networks. Remarkably, given some plausible scaling assumptions on the NTK spectra and spectral decomposition of the labels -- learning is optimal in a scaling sense.
  arXiv  Detail & Related papers  (2023-07-27T06:59:46Z)
• Globally Optimal Training of Neural Networks with Threshold Activation Functions [63.03759813952481]
  We study weight decay regularized training problems of deep neural networks with threshold activations. We derive a simplified convex optimization formulation when the dataset can be shattered at a certain layer of the network.
  arXiv  Detail & Related papers  (2023-03-06T18:59:13Z)
• Neural Clamping: Joint Input Perturbation and Temperature Scaling for Neural Network Calibration [62.4971588282174]
  We propose a new post-processing calibration method called Neural Clamping. Our empirical results show that Neural Clamping significantly outperforms state-of-the-art post-processing calibration methods.
  arXiv  Detail & Related papers  (2022-09-23T14:18:39Z)
• Understanding of the properties of neural network approaches for transient light curve approximations [37.91290708320157]
  This paper presents a search for the best-performing methods to approximate the observed light curves over time and wavelength. Test datasets include simulated PLAsTiCC and real Zwicky Transient Facility Bright Transient Survey light curves of transients.
  arXiv  Detail & Related papers  (2022-09-15T18:00:08Z)
• Light curve completion and forecasting using fast and scalable Gaussian processes (MuyGPs) [0.0]
  Ground-based observations from commercial off the shelf (COTS) cameras remain inexpensive compared to higher precision instruments. limited sensor availability combined with noisier observations can produce gappy time-series data. Deep Neural Networks (DNNs) have become the tool of choice due to their empirical success at learning complex nonlinear embeddings.
  arXiv  Detail & Related papers  (2022-08-31T01:52:00Z)
• Supernova Light Curves Approximation based on Neural Network Models [53.180678723280145]
  Photometric data-driven classification of supernovae becomes a challenge due to the appearance of real-time processing of big data in astronomy. Recent studies have demonstrated the superior quality of solutions based on various machine learning models. We study the application of multilayer perceptron (MLP), bayesian neural network (BNN), and normalizing flows (NF) to approximate observations for a single light curve.
  arXiv  Detail & Related papers  (2022-06-27T13:46:51Z)
• Real-time gravitational-wave science with neural posterior estimation [64.67121167063696]
  We demonstrate unprecedented accuracy for rapid gravitational-wave parameter estimation with deep learning. We analyze eight gravitational-wave events from the first LIGO-Virgo Gravitational-Wave Transient Catalog. We find very close quantitative agreement with standard inference codes, but with inference times reduced from O(day) to a minute per event.
  arXiv  Detail & Related papers  (2021-06-23T18:00:05Z)
• Factorized Neural Processes for Neural Processes: $K$-Shot Prediction of Neural Responses [9.792408261365043]
  We develop a Factorized Neural Process to infer a neuron's tuning function from a small set of stimulus-response pairs. We show on simulated responses that the predictions and reconstructed receptive fields from the Neural Process approach ground truth with increasing number of trials. We believe this novel deep learning systems identification framework will facilitate better real-time integration of artificial neural network modeling into neuroscience experiments.
  arXiv  Detail & Related papers  (2020-10-22T15:43:59Z)
• Predicting atmospheric optical properties for radiative transfer computations using neural networks [0.0]
  We develop a machine learning-based parametrization for the gaseous optical properties by training neural networks to emulate a modern radiation parameterization (RRTMGP) Our neural network-based gas optics parametrization is up to 4 times faster than RRTMGP, depending on the size of the neural networks. We conclude that our machine learning-based parametrization can speed-up radiative transfer computations whilst retaining high accuracy.
  arXiv  Detail & Related papers  (2020-05-05T15:00:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.