论文标题
Lorentz Group ateriant粒子物理神经网络
Lorentz Group Equivariant Neural Network for Particle Physics
论文作者
论文摘要
我们提出了一种神经网络体系结构，该架构在洛伦兹组下的转换方面完全等不解，这是物理学时空的基本对称性。该体系结构基于Lorentz群体的有限维表示理论，而均值非线性涉及张量产物。对于粒子物理学中的分类任务，我们证明了这种模棱两可的架构会导致更简单的模型，这些模型比使用CNNS和Point Cloud方法的领先方法相对较少，并且在物理上更容易解释。该网络的竞争性能在公共分类数据集[27]上证明了标记顶级夸克腐烂，鉴于质子 - 普罗顿碰撞中产生的喷气成分的能量。
We present a neural network architecture that is fully equivariant with respect to transformations under the Lorentz group, a fundamental symmetry of space and time in physics. The architecture is based on the theory of the finite-dimensional representations of the Lorentz group and the equivariant nonlinearity involves the tensor product. For classification tasks in particle physics, we demonstrate that such an equivariant architecture leads to drastically simpler models that have relatively few learnable parameters and are much more physically interpretable than leading approaches that use CNNs and point cloud approaches. The competitive performance of the network is demonstrated on a public classification dataset [27] for tagging top quark decays given energy-momenta of jet constituents produced in proton-proton collisions.
