Transformer trained on S10 permutation prediction from transpositions generalizes to S25 with near 100% accuracy using identity augmentation and partitioned windows.
Lacoin,Mixing Time and Cutoff for the Adjacent Transposition Shuf- fle and the Simple Exclusion, The Annals of Probability,44(2), 1426– 1487, (2016)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Learning the symmetric group: large from small
Transformer trained on S10 permutation prediction from transpositions generalizes to S25 with near 100% accuracy using identity augmentation and partitioned windows.