2 papers
cs.LG2024
Theoretical limitations of multi-layer Transformer
Lijie Chen, Binghui Peng, Hongxun Wu
Transformers, especially the decoder-only variants, are the backbone of most modern large language models; yet we do not have much understanding of their expressive power except fo…
cs.DS2024
Sample-Based Matroid Prophet Inequalities
Hu Fu, Pinyan Lu, Zhihao Gavin Tang +3
We study matroid prophet inequalities when distributions are unknown and accessible only through samples. While single-sample prophet inequalities for special matroids are known, n…