Discovering Lie Groups with Flow Matching
By: Jung Yeon Park , Yuxuan Chen , Floor Eijkelboom and more
Symmetry is fundamental to understanding physical systems, and at the same time, can improve performance and sample efficiency in machine learning. Both pursuits require knowledge of the underlying symmetries in data. To address this, we propose learning symmetries directly from data via flow matching on Lie groups. We formulate symmetry discovery as learning a distribution over a larger hypothesis group, such that the learned distribution matches the symmetries observed in data. Relative to previous works, our method, \lieflow, is more flexible in terms of the types of groups it can discover and requires fewer assumptions. Experiments on 2D and 3D point clouds demonstrate the successful discovery of discrete groups, including reflections by flow matching over the complex domain. We identify a key challenge where the symmetric arrangement of the target modes causes ``last-minute convergence,'' where samples remain stationary until relatively late in the flow, and introduce a novel interpolation scheme for flow matching for symmetry discovery.
Similar Papers
Lie Group Symmetry Discovery and Enforcement Using Vector Fields
Machine Learning (Stat)
Teaches computers to find hidden patterns faster.
Equivariant Flow Matching for Symmetry-Breaking Bifurcation Problems
Machine Learning (CS)
Lets computers learn many possible answers.
Flow Matching on Lie Groups
Differential Geometry
Makes computers create realistic 3D shapes from data.