P. Soldin

R. Abbasi, M. Ackermann, J. Adams et al.

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.

M. Bachlechner, T. Birkenfeld, P. Soldin et al.

Convolutional graph networks are used in particle physics for effective event reconstructions and classifications. However, their performances can be limited by the considerable amount of sensors used in modern particle detectors if applied to sensor-level data. We present a pooling scheme that uses partitioning to create pooling kernels on graphs, similar to pooling on images. Partition pooling can be used to adopt successful image recognition architectures for graph neural network applications in particle physics. The reduced computational resources allow for deeper networks and more extensive hyperparameter optimizations. To show its applicability, we construct a convolutional graph network with partition pooling that reconstructs simulated interaction vertices for an idealized neutrino detector. The pooling network yields improved performance and is less susceptible to overfitting than a similar network without pooling. The lower resource requirements allow the construction of a deeper network with further improved performance.