<ul><li>CTSketch is a novel, scalable neurosymbolic learning algorithm for training neural networks using end-to-end input-output labels.</li><li>CTSketch decomposes the symbolic program into sub-programs and summarizes each sub-program with a sketched tensor to improve scalability.</li><li>The algorithm approximates the output distribution of the program using simple tensor operations over input distributions and summaries.</li><li>CTSketch achieves high accuracy on tasks involving over one thousand inputs, pushing neurosymbolic learning to new scales.</li></ul>

CTSketch: Compositional Tensor Sketching for Scalable Neurosymbolic Learning

Discover more