Speaker
Description
Machine learning offers an alternative to conventional iterative algorithms for lattice gauge fixing, with the potential to reduce computational cost for large lattice volumes. Building upon our previous work, we perform a systematic scan of convolutional neural network architectures for lattice gauge fixing, in which the gauge transformation matrices are constructed from Wilson lines with multiple lengths. We explore the trade-off between gauge-fixing performance and computational efficiency, identifying compact models that maintain competitive performance while reducing computational cost, particularly on large lattices. We present preliminary results on SU(3) gauge ensembles, demonstrating that an appropriate model design can provide an efficient and scalable approach to lattice gauge fixing.