Searcharxiv⌕ Search

arXiv subjects

Maximilian Dax

Publications and source records attributed to Maximilian Dax.

At least 19 recordsLinked to original sources
arXiv2026

An Introduction to Bayesian and Frequentist Simulation-Based Inference with Machine Learning

Simulation-based inference (SBI) with machine learning is an increasingly important tool for solving inverse problems in science and engineering, including parameter inference and the inversion of detector effects. We provide an overview of the Bayesian and frequentist statistical frameworks, describe how machine-learning-based SBI methods, such as neural posterior estimation and neural likelihood estimation, can be used for parameter estimation within these frameworks, and show that the same methods can also be applied to Empirical Bayes or unfolding tasks. We also discuss how to validate inference results and the limitations of SBI with machine learning.

cs.LG↗
arXiv2026

End-to-End Population Inference from Gravitational-Wave Strain using Transformers

The population of compact binaries encodes information about their astrophysical origins and the expansion of the universe. Hierarchical Bayesian methods infer these properties by combining single-event posteriors. As catalogs grow, however, this approach becomes computationally expensive and is subject to increasing Monte Carlo uncertainty. We introduce Dingo-Pop, a simulation-based framework that infers population posteriors directly from gravitational-wave strain data. The data for each event are embedded into low-dimensional tokens and combined using a transformer trained on simulated catalogs subject to selection effects. This enables (i) population inference without per-event Monte Carlo sampling noise, (ii) amortization across variable catalog sizes using a single network, and (iii) end-to-end inference in about one second. We train a network for catalog sizes of 25 to 1000 events, and obtain well-calibrated posteriors consistent with traditional methods. By avoiding per-event analyses that can take hours to days, Dingo-Pop enables new classes of large-scale injection studies; as an application, we examine how spectral-siren Hubble constant uncertainties change with catalog size.

gr-qc↗
arXiv2026

Eccentricity constraints disfavor single-single capture in nuclear star clusters as the origin of all LIGO-Virgo-KAGRA binary black holes

Multiple formation pathways have been proposed for the origin of binary black holes (BBHs). These include isolated binary evolution and dynamical assembly in dense stellar environments such as nuclear or globular star clusters. Yet, the fraction of BBHs originating from each channel remains uncertain. One way to constrain this fraction is by investigating the orbital eccentricities of the BH coalescences detected by the LIGO-Virgo-KAGRA (LVK) Collaboration. We analyze 84 BBHs from the first part of the fourth LVK observing run (O4a) using a multipolar, eccentric, aligned-spin effective-one-body waveform model. We perform parameter inference with neural posterior estimation and nested sampling. After incorporating astrophysical prior odds and comparing to the quasicircular precessing-spin hypothesis, we find that no candidates reach a high enough significance to claim a confident detection of eccentricity. We use these upper limits to explore a model, in which all O4a BBHs originate from single-single gravitational wave (GW) captures. We perform hierarchical inference on the velocity dispersion of the host environment of the BBHs and find $\sigma$ < 19.7 km/s (95% credible upper bound). This disfavors single-single capture in nuclear star clusters (approximately 20-200 km/s) as the dominant source of all observed BBH mergers. Our analysis also jointly infers the mass, spin and redshift distributions and takes into account selection effects due to using quasi-circular templates for BBH detection. Our results place improved constraints on the number of eccentric BBHs and highlight the importance of eccentricity measurements in disentangling compact-binary formation channels in current and future GW detectors.

astro-ph.HE↗
arXiv2025

Flexible Gravitational-Wave Parameter Estimation with Transformers

Gravitational-wave data analysis relies on accurate and efficient methods to extract physical information from noisy detector signals, yet the increasing rate and complexity of observations represent a growing challenge. Deep learning provides a powerful alternative to traditional inference, but existing neural models typically lack the flexibility to handle variations in data analysis settings. Such variations accommodate imperfect observations or are required for specialized tests, and could include changes in detector configurations, overall frequency ranges, or localized cuts. We introduce a flexible transformer-based architecture paired with a training strategy that enables adaptation to diverse analysis settings at inference time. Applied to parameter estimation, we demonstrate that a single flexible model, called Dingo-T1, can (i) analyze 48 gravitational-wave events from the third LIGO-Virgo-KAGRA Observing Run under a wide range of analysis configurations, (ii) enable systematic studies of how detector and frequency configurations impact inferred posteriors, and (iii) perform inspiral-merger-ringdown consistency tests probing general relativity. Dingo-T1 also improves median sample efficiency on real events from a baseline of 1.4% to 4.2%. Our approach thus demonstrates flexible and scalable inference with a principled framework for handling missing or incomplete data, key capabilities for current and next-generation observatories.

gr-qc↗
arXiv2025

Fast and accurate parameter estimation of high-redshift sources with the Einstein Telescope

The Einstein Telescope (ET), along with other third-generation gravitational wave (GW) detectors, will be a key instrument for detecting GWs in the coming decades. However, analyzing the data and estimating source parameters will be challenging, especially given the large number of expected detections-on the order of $10^5$ per year-which makes current methods based on stochastic sampling impractical. In this work, we use Dingo-IS to perform neural posterior estimation (NPE) of high-redshift events detectable with ET in its triangular configuration. NPE is a likelihood-free inference technique that leverages normalizing flows to approximate posterior distributions. After training, inference is fast, requiring only a few minutes per source, and accurate, as corrected through importance sampling and validated against standard Bayesian inference methods. To confirm previous findings on the ability to estimate parameters for high-redshift sources with ET, we compare NPE results with predictions from the Fisher information matrix (FIM) approximation. We find that NPE correctly recovers the eight degenerate sky modes induced by the triangular detector geometry, missed by the FIM analysis, resulting in an underestimation of sky localization uncertainties for most sources. FIM also overestimates the uncertainty in luminosity distance by a factor of $\sim 3$ on average when the injected luminosity distance is $d^{\mathrm{inj}}_{\mathrm{L}} > 10^5~$Mpc, further confirming that ET will be particularly well suited for studying the early Universe.

astro-ph.HE↗
arXiv2025

Reparameterized LLM Training via Orthogonal Equivalence Transformation

While large language models (LLMs) are driving the rapid advancement of artificial intelligence, effectively and reliably training these large models remains one of the field's most significant challenges. To address this challenge, we propose POET, a novel reParameterized training algorithm that uses Orthogonal Equivalence Transformation to optimize neurons. Specifically, POET reparameterizes each neuron with two learnable orthogonal matrices and a fixed random weight matrix. Because of its provable preservation of spectral properties of weight matrices, POET can stably optimize the objective function with improved generalization. We further develop efficient approximations that make POET flexible and scalable for training large-scale neural networks. Extensive experiments validate the effectiveness and scalability of POET in training LLMs.

cs.LG↗
arXiv2025

Synthesizing 3D Abstractions by Inverting Procedural Buildings with Transformers

We generate abstractions of buildings, reflecting the essential aspects of their geometry and structure, by learning to invert procedural models. We first build a dataset of abstract procedural building models paired with simulated point clouds and then learn the inverse mapping through a transformer. Given a point cloud, the trained transformer then infers the corresponding abstracted building in terms of a programmatic language description. This approach leverages expressive procedural models developed for gaming and animation, and thereby retains desirable properties such as efficient rendering of the inferred abstractions and strong priors for regularity and symmetry. Our approach achieves good reconstruction accuracy in terms of geometry and structure, as well as structurally consistent inpainting.

cs.CV↗
arXiv2024

Flow Matching for Atmospheric Retrieval of Exoplanets: Where Reliability meets Adaptive Noise Levels

Inferring atmospheric properties of exoplanets from observed spectra is key to understanding their formation, evolution, and habitability. Since traditional Bayesian approaches to atmospheric retrieval (e.g., nested sampling) are computationally expensive, a growing number of machine learning (ML) methods such as neural posterior estimation (NPE) have been proposed. We seek to make ML-based atmospheric retrieval (1) more reliable and accurate with verified results, and (2) more flexible with respect to the underlying neural networks and the choice of the assumed noise models. First, we adopt flow matching posterior estimation (FMPE) as a new ML approach to atmospheric retrieval. FMPE maintains many advantages of NPE, but provides greater architectural flexibility and scalability. Second, we use importance sampling (IS) to verify and correct ML results, and to compute an estimate of the Bayesian evidence. Third, we condition our ML models on the assumed noise level of a spectrum (i.e., error bars), thus making them adaptable to different noise models. Both our noise level-conditional FMPE and NPE models perform on par with nested sampling across a range of noise levels when tested on simulated data. FMPE trains about 3 times faster than NPE and yields higher IS efficiencies. IS successfully corrects inaccurate ML results, identifies model failures via low efficiencies, and provides accurate estimates of the Bayesian evidence. FMPE is a powerful alternative to NPE for fast, amortized, and parallelizable atmospheric retrieval. IS can verify results, thus helping to build confidence in ML-based approaches, while also facilitating model comparison via the evidence ratio. Noise level conditioning allows design studies for future instruments to be scaled up, for example, in terms of the range of signal-to-noise ratios.

astro-ph.IM↗
arXiv2024

Real-time gravitational-wave inference for binary neutron stars using machine learning

Mergers of binary neutron stars (BNSs) emit signals in both the gravitational-wave (GW) and electromagnetic (EM) spectra. Famously, the 2017 multi-messenger observation of GW170817 led to scientific discoveries across cosmology, nuclear physics, and gravity. Central to these results were the sky localization and distance obtained from GW data, which, in the case of GW170817, helped to identify the associated EM transient, AT 2017gfo, 11 hours after the GW signal. Fast analysis of GW data is critical for directing time-sensitive EM observations; however, due to challenges arising from the length and complexity of signals, it is often necessary to make approximations that sacrifice accuracy. Here, we present a machine learning framework that performs complete BNS inference in just one second without making any such approximations. Our approach enhances multi-messenger observations by providing (i) accurate localization even before the merger; (ii) improved localization precision by $\sim30\%$ compared to approximate low-latency methods; and (iii) detailed information on luminosity distance, inclination, and masses, which can be used to prioritize expensive telescope time. Additionally, the flexibility and reduced cost of our method open new opportunities for equation-of-state studies. Finally, we demonstrate that our method scales to extremely long signals, up to an hour in length, thus serving as a blueprint for data analysis for next-generation ground- and space-based detectors.

gr-qc↗
arXiv2024

Fast and Reliable Probabilistic Reflectometry Inversion with Prior-Amortized Neural Posterior Estimation

Reconstructing the structure of thin films and multilayers from measurements of scattered X-rays or neutrons is key to progress in physics, chemistry, and biology. However, finding all structures compatible with reflectometry data is computationally prohibitive for standard algorithms, which typically results in unreliable analysis with only a single potential solution identified. We address this lack of reliability with a probabilistic deep learning method that identifies all realistic structures in seconds, setting new standards in reflectometry. Our method, Prior-Amortized Neural Posterior Estimation (PANPE), combines simulation-based inference with novel adaptive priors that inform the inference network about known structural properties and controllable experimental conditions. PANPE networks support key scenarios such as high-throughput sample characterization, real-time monitoring of evolving structures, or the co-refinement of several experimental data sets, and can be adapted to provide fast, reliable, and flexible inference across many other inverse problems.

physics.app-ph↗
arXiv2024

Evidence for eccentricity in the population of binary black holes observed by LIGO-Virgo-KAGRA

Binary black holes (BBHs) in eccentric orbits produce distinct modulations in gravitational waves (GWs); measuring orbital eccentricity provides evidence for dynamical binary formation channels. We analyze 57 GW events from the LIGO-Virgo-KAGRA (LVK) O1-O3 observing runs using a multipolar aligned-spin inspiral-merger-ringdown waveform with two eccentric parameters: eccentricity and relativistic anomaly (assuming a quasi-circular merger-ringdown), made computationally feasible by the machine-learning code \texttt{DINGO}, which accelerates inference by 2-3 orders of magnitude. First, with a uniform eccentricity prior, eccentric vs. quasi-circular aligned-spin $\log_{10}$ Bayes factors are 1.84-4.75 (depending on glitch mitigation) for GW200129, 3.0 for GW190701 and 1.77 for GW200208_22. We infer $e_{\text{gw, 10Hz}}$ $(e_{\text{gw, 20Hz}})$ to be $0.27_{-0.12}^{+0.10}$ ($0.16_{-0.05}^{+0.04}$) to $0.17_{-0.13}^{+0.14}$ ($0.1_{-0.04}^{+0.05}$) for GW200129, $0.54_{-0.30}^{+0.12}$ ($0.31_{-0.13}^{+0.12}$) for GW190701 and $0.39_{-0.23}^{+0.23}$ ($0.21_{-0.08}^{+0.08}$) for GW200208_22. Second, eccentric aligned-spin vs. quasi-circular precessing-spin $\log_{10}$ Bayes factors are 1.43-4.92 for GW200129, 2.61 for GW190701 and 1.23 for GW200208_22. Third, GW190521 shows no evidence for eccentricity ($\log_{10}$ Bayes factor 0.04). Fourth, neglecting spin-precession with an astrophysically-motivated prior on the eccentric BBH rate, the probability of one of the 57 events being eccentric exceeds 99.5\% or $(100-8.4\times10^{-4})$\% (depending on glitch mitigation). Fifth, we study parameter estimation impacts of neglecting eccentricity in quasi-circular models or higher modes in eccentric models. These results underscore the inclusion of eccentric parameters in BBH characterization for upcoming LVK runs and future ground- and space-based detectors probing more diverse BBH populations.

gr-qc↗
arXiv2023

Inferring Atmospheric Properties of Exoplanets with Flow Matching and Neural Importance Sampling

Atmospheric retrievals (AR) characterize exoplanets by estimating atmospheric parameters from observed light spectra, typically by framing the task as a Bayesian inference problem. However, traditional approaches such as nested sampling are computationally expensive, thus sparking an interest in solutions based on machine learning (ML). In this ongoing work, we first explore flow matching posterior estimation (FMPE) as a new ML-based method for AR and find that, in our case, it is more accurate than neural posterior estimation (NPE), but less accurate than nested sampling. We then combine both FMPE and NPE with importance sampling, in which case both methods outperform nested sampling in terms of accuracy and simulation efficiency. Going forward, our analysis suggests that simulation-based inference with likelihood-based importance sampling provides a framework for accurate and efficient AR that may become a valuable tool not only for the analysis of observational data from existing telescopes, but also for the development of new missions and instruments.

astro-ph.IM↗
arXiv2023

Flow Matching for Scalable Simulation-Based Inference

Neural posterior estimation methods based on discrete normalizing flows have become established tools for simulation-based inference (SBI), but scaling them to high-dimensional problems can be challenging. Building on recent advances in generative modeling, we here present flow matching posterior estimation (FMPE), a technique for SBI using continuous normalizing flows. Like diffusion models, and in contrast to discrete flows, flow matching allows for unconstrained architectures, providing enhanced flexibility for complex data modalities. Flow matching, therefore, enables exact density evaluation, fast training, and seamless scalability to large architectures--making it ideal for SBI. We show that FMPE achieves competitive performance on an established SBI benchmark, and then demonstrate its improved scalability on a challenging scientific problem: for gravitational-wave inference, FMPE outperforms methods based on comparable discrete flows, reducing training time by 30% with substantially improved accuracy. Our work underscores the potential of FMPE to enhance performance in challenging inference scenarios, thereby paving the way for more advanced applications to scientific problems.

cs.LG↗
arXiv2023

Applications of Deep Learning to physics workflows

Modern large-scale physics experiments create datasets with sizes and streaming rates that can exceed those from industry leaders such as Google Cloud and Netflix. Fully processing these datasets requires both sufficient compute power and efficient workflows. Recent advances in Machine Learning (ML) and Artificial Intelligence (AI) can either improve or replace existing domain-specific algorithms to increase workflow efficiency. Not only can these algorithms improve the physics performance of current algorithms, but they can often be executed more quickly, especially when run on coprocessors such as GPUs or FPGAs. In the winter of 2023, MIT hosted the Accelerating Physics with ML at MIT workshop, which brought together researchers from gravitational-wave physics, multi-messenger astrophysics, and particle physics to discuss and share current efforts to integrate ML tools into their workflows. The following white paper highlights examples of algorithms and computing frameworks discussed during this workshop and summarizes the expected computing needs for the immediate future of the involved fields.

hep-ex↗
arXiv2023

Group equivariant neural posterior estimation

Simulation-based inference with conditional neural density estimators is a powerful approach to solving inverse problems in science. However, these methods typically treat the underlying forward model as a black box, with no way to exploit geometric properties such as equivariances. Equivariances are common in scientific models, however integrating them directly into expressive inference networks (such as normalizing flows) is not straightforward. We here describe an alternative method to incorporate equivariances under joint transformations of parameters and data. Our method -- called group equivariant neural posterior estimation (GNPE) -- is based on self-consistently standardizing the "pose" of the data while estimating the posterior over parameters. It is architecture-independent, and applies both to exact and approximate equivariances. As a real-world application, we use GNPE for amortized inference of astrophysical binary black hole systems from gravitational-wave observations. We show that GNPE achieves state-of-the-art accuracy while reducing inference times by three orders of magnitude.

cs.LG↗
arXiv2023

Real-time gravitational-wave science with neural posterior estimation

We demonstrate unprecedented accuracy for rapid gravitational-wave parameter estimation with deep learning. Using neural networks as surrogates for Bayesian posterior distributions, we analyze eight gravitational-wave events from the first LIGO-Virgo Gravitational-Wave Transient Catalog and find very close quantitative agreement with standard inference codes, but with inference times reduced from O(day) to a minute per event. Our networks are trained using simulated data, including an estimate of the detector-noise characteristics near the event. This encodes the signal and noise models within millions of neural-network parameters, and enables inference for any observed data consistent with the training distribution, accounting for noise nonstationarity from event to event. Our algorithm -- called "DINGO" -- sets a new standard in fast-and-accurate inference of physical parameters of detected gravitational-wave events, which should enable real-time data analysis without sacrificing accuracy.

gr-qc↗
arXiv2023

Neural Importance Sampling for Rapid and Reliable Gravitational-Wave Inference

We combine amortized neural posterior estimation with importance sampling for fast and accurate gravitational-wave inference. We first generate a rapid proposal for the Bayesian posterior using neural networks, and then attach importance weights based on the underlying likelihood and prior. This provides (1) a corrected posterior free from network inaccuracies, (2) a performance diagnostic (the sample efficiency) for assessing the proposal and identifying failure cases, and (3) an unbiased estimate of the Bayesian evidence. By establishing this independent verification and correction mechanism we address some of the most frequent criticisms against deep learning for scientific inference. We carry out a large study analyzing 42 binary black hole mergers observed by LIGO and Virgo with the SEOBNRv4PHM and IMRPhenomXPHM waveform models. This shows a median sample efficiency of $\approx 10\%$ (two orders-of-magnitude better than standard samplers) as well as a ten-fold reduction in the statistical uncertainty in the log evidence. Given these advantages, we expect a significant impact on gravitational-wave inference, and for this approach to serve as a paradigm for harnessing deep learning methods in scientific applications.

gr-qc↗
arXiv2022

Adapting to noise distribution shifts in flow-based gravitational-wave inference

Deep learning techniques for gravitational-wave parameter estimation have emerged as a fast alternative to standard samplers $\unicode{x2013}$ producing results of comparable accuracy. These approaches (e.g., DINGO) enable amortized inference by training a normalizing flow to represent the Bayesian posterior conditional on observed data. By conditioning also on the noise power spectral density (PSD) they can even account for changing detector characteristics. However, training such networks requires knowing in advance the distribution of PSDs expected to be observed, and therefore can only take place once all data to be analyzed have been gathered. Here, we develop a probabilistic model to forecast future PSDs, greatly increasing the temporal scope of DINGO networks. Using PSDs from the second LIGO-Virgo observing run (O2) $\unicode{x2013}$ plus just a single PSD from the beginning of the third (O3) $\unicode{x2013}$ we show that we can train a DINGO network to perform accurate inference throughout O3 (on 37 real events). We therefore expect this approach to be a key component to enable the use of deep learning techniques for low-latency analyses of gravitational waves.

gr-qc↗