Showing cs.LGShow all
2 papers · 1 filter
cs.LG2024
Can Transformers Reason Logically? A Study in SAT Solving
Leyan Pan, Vijay Ganesh, Jacob Abernethy +2
We formally study the logical reasoning capabilities of decoder-only Transformers in the context of the boolean satisfiability (SAT) problem. First, we prove by construction that d…
cs.LG2023
Towards Understanding Neural Collapse: The Effects of Batch Normalization and Weight Decay
Leyan Pan, Xinyuan Cao
Neural Collapse (NC) is a geometric structure recently observed at the terminal phase of training deep neural networks, which states that last-layer feature vectors for the same cl…