Neural posterior estimation of the neutrino direction in IceCube using transformer-encoded normalizing flows on the sphere

• URL: http://arxiv.org/abs/2604.19846v1
• Date: Tue, 21 Apr 2026 12:27:26 GMT
• Title: Neural posterior estimation of the neutrino direction in IceCube using transformer-encoded normalizing flows on the sphere
• Abstract summary: We discuss neural posterior estimation of the neutrino direction via a transformer encoder that maps to a normalizing flow on the 2-sphere.<n>It achieves a new state-of-the-art angular resolution for the two main event morphologies in IceCube - tracks and showers.<n>All-sky scans can be performed within seconds rather than hours, and take constant computation time.
• Score: 6.9589689673109385
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: IceCube is a cubic-kilometer-scale neutrino detector located at the geographic South Pole. A precise directional reconstruction of IceCube neutrinos is vital for associations with astronomical objects. In this context, we discuss neural posterior estimation of the neutrino direction via a transformer encoder that maps to a normalizing flow on the 2-sphere. It achieves a new state-of-the-art angular resolution for the two main event morphologies in IceCube - tracks and showers - while being significantly faster than traditional B-spline-based likelihood reconstructions. All-sky scans can be performed within seconds rather than hours, and take constant computation time, regardless of whether the posterior extent is arc-minutes or spans the whole sky. We utilize a combination of $C^2$-smooth rational-quadratic splines, scale transformations and rotations to define a novel spherical normalizing-flow distribution whose parameters are predicted as a whole as the output of the transformer encoder. We test several structural choices diverting from the vanilla transformer architecture. In particular, we find dual residual streams, nonlinear QKV projection and a separate class token with its own cross-attention processing to boost test-time performance. The angular resolution for both showers and tracks improves substantially over the whole trained energy range from 100 GeV to 100 PeV. At 100 TeV deposited energy, for example, the median angular resolution improves by a factor of $1.3$ for throughgoing tracks, by a factor of $1.7$ for showers and by a factor of $2.5$ for starting tracks compared to state-of-the art likelihood reconstructions based on B-splines. While previous machine-learning (ML) efforts have managed to obtain competitive shower resolutions, this is the first time an ML-based method outperforms likelihood-based muon reconstructions above 100 GeV.

Related papers

• Round-Trip Consistency: Bidirectional Diffusion Models Can Predict Their Own Rollout Errors [51.56484100374058]
  Autoregressive models accumulate error over long rollouts, yet at deployment there is no ground truth to measure it against.<n>We train a single conditional latent diffusion model that steps a dynamical system forward or backward in time via a direction flag.<n>We show that this bidirectionality supplies a measurement-free test-time error signal.
  arXiv  Detail & Related papers  (2026-08-01T13:49:46Z)
• Predicting the Slow Drift of Nuclear Spin Noise in Semiconductor Spin Qubits [0.0]
  The dynamics of a nuclear spin bath generates magnetic noise that is a key contributor to the decoherence of electron spinbits in quantum dots.<n>We extend the cluster correlation expansion (CCE) technique to incorporate treatments of cluster dynamics in order to efficiently predict slow drifting Overhauser fields over longer time scales.
  arXiv  Detail & Related papers  (2026-07-28T17:31:27Z)
• Machine Learning-Based Reconstruction for Resistive Silicon Sensors [53.365453214937496]
  We study machine-learning-based reconstruction and compression for resistive silicon sensors.<n>We use full-waveform information from correlated pads to regularise the reconstruction and extract spatial information.<n>We first introduce recurrent neural network models based on LSTM layers, which provide a proof-of-concept implementation for full-waveform reconstruction.
  arXiv  Detail & Related papers  (2026-07-13T14:03:26Z)
• N-vium: Mixture-of-Exits Transformer for Accelerated Exact Generation [68.47358899451255]
  N-vium is a mixture-of-exits transformer that partially parallelizes computation across depth on standard hardware.<n>N-vium attaches prediction heads at multiple depths and defines the next-token distribution as a learned mixture over these exits.
  arXiv  Detail & Related papers  (2026-05-13T08:46:17Z)
• Total Generalized Variation regularization closes the gap between neural-eld and classical methods in seismic travel-time tomography [0.0]
  Traveltime tomography forces a tradeoff between mesh resolution and stability in which the regularizer choice dominates what can be recovered.<n>We introduce MIMIR, a differentiable framework that represents the 2D velocity field as a Fourier-feature neural network.
  arXiv  Detail & Related papers  (2026-05-11T04:13:52Z)
• Graph Neural ODE Digital Twins for Control-Oriented Reactor Thermal-Hydraulic Forecasting Under Partial Observability [6.370970195988317]
  Real-time supervisory control of advanced reactors requires accurate forecasting of plant-wide thermalhydraulic states.<n>We present a physics-informed message-passing Differential Neural Network and a Neural Ordinary Equation (GNN-ODE)<n>The GNN-ODE surrogate achieves satisfactory results for the system dynamics prediction.
  arXiv  Detail & Related papers  (2026-04-08T16:58:14Z)
• End-to-end event reconstruction for precision physics at future colliders [0.39998518782208786]
  Future collider experiments require unprecedented precision in measurements of Higgs, electroweak, and observable flavours.<n>Current particle flow algorithms rely on detector specific clustering, limiting flexibility during detector design.<n>Here we present an end-to-end global event reconstruction approach that maps charged particle tracks and calorimeter and muon hits directly to particle level objects.
  arXiv  Detail & Related papers  (2026-03-04T13:55:04Z)
• Quantum Phaselift [0.0]
  We introduce a lifting-based framework that estimates the rank-one matrix $Z = f fdagger$ rather than estimating $f$ directly.<n>We prove that a $O(1)$ bandwidth suffices for generic signals, leading to substantial savings in controlled operations.<n>We numerically demonstrate that high-quality recovery is possible for the 2D Fermi-Hubbard and 2D transverse-field Ising model signals of size exceeding 100 time points.
  arXiv  Detail & Related papers  (2026-02-09T19:09:57Z)
• FFT-Accelerated Auxiliary Variable MCMC for Fermionic Lattice Models: A Determinant-Free Approach with $O(N\log N)$ Complexity [52.3171766248012]
  We introduce a Markov Chain Monte Carlo (MCMC) algorithm that dramatically accelerates the simulation of quantum many-body systems.<n>We validate our algorithm on benchmark quantum physics problems, accurately reproducing known theoretical results.<n>Our work provides a powerful tool for large-scale probabilistic inference and opens avenues for physics-inspired generative models.
  arXiv  Detail & Related papers  (2025-10-13T07:57:21Z)
• Bayesian Circular Regression with von Mises Quasi-Processes [57.88921637944379]
  In this work we explore a family of expressive and interpretable distributions over circle-valued random functions.<n>For posterior inference, we introduce a new Stratonovich-like augmentation that lends itself to fast Gibbs sampling.<n>We present experiments applying this model to the prediction of wind directions and the percentage of the running gait cycle as a function of joint angles.
  arXiv  Detail & Related papers  (2024-06-19T01:57:21Z)
• Learning with Norm Constrained, Over-parameterized, Two-layer Neural Networks [54.177130905659155]
  Recent studies show that a reproducing kernel Hilbert space (RKHS) is not a suitable space to model functions by neural networks. In this paper, we study a suitable function space for over- parameterized two-layer neural networks with bounded norms.
  arXiv  Detail & Related papers  (2024-04-29T15:04:07Z)
• SGFormer: Spherical Geometry Transformer for 360 Depth Estimation [52.23806040289676]
  Panoramic distortion poses a significant challenge in 360 depth estimation.<n>We propose a spherical geometry transformer, named SGFormer, to address the above issues.<n>We also present a query-based global conditional position embedding to compensate for spatial structure at varying resolutions.
  arXiv  Detail & Related papers  (2024-04-23T12:36:24Z)
• Kronecker-Factored Approximate Curvature for Modern Neural Network Architectures [85.76673783330334]
  Two different settings of linear weight-sharing layers motivate two flavours of Kronecker-Factored Approximate Curvature (K-FAC) We show they are exact for deep linear networks with weight-sharing in their respective setting. We observe little difference between these two K-FAC variations when using them to train both a graph neural network and a vision transformer.
  arXiv  Detail & Related papers  (2023-11-01T16:37:00Z)
• Neural Inference of Gaussian Processes for Time Series Data of Quasars [72.79083473275742]
  We introduce a new model that enables it to describe quasar spectra completely. We also introduce a new method of inference of Gaussian process parameters, which we call $textitNeural Inference$. The combination of both the CDRW model and Neural Inference significantly outperforms the baseline DRW and MLE.
  arXiv  Detail & Related papers  (2022-11-17T13:01:26Z)
• Direction of Arrival Estimation of Sound Sources Using Icosahedral CNNs [10.089520556398574]
  We present a new model for Direction of Arrival (DOA) estimation of sound sources based on an Icosahedral Convolutional Neural Network (CNN) This icosahedral CNN is equivariant to the 60 rotational symmetries of the icosahedron, which represent a good approximation of the continuous space of spherical rotations. We prove that using models that fit the equivariances of the problem allows us to outperform other state-of-the-art models with a lower computational cost and more robustness.
  arXiv  Detail & Related papers  (2022-03-31T10:52:19Z)
• Gravitational-wave parameter estimation with autoregressive neural network flows [0.0]
  We introduce the use of autoregressive normalizing flows for rapid likelihood-free inference of binary black hole system parameters from gravitational-wave data with deep neural networks. A normalizing flow is an invertible mapping on a sample space that can be used to induce a transformation from a simple probability distribution to a more complex one. We build a more powerful latent variable model by incorporating autoregressive flows within the variational autoencoder framework.
  arXiv  Detail & Related papers  (2020-02-18T15:44:04Z)

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.