2 papers
cs.LG2026
Transformer Approximations from ReLUs
Jerry Yao-Chieh Hu, Mingcheng Lu, Yi-Chen Lee +1
We provide a systematic recipe for translating ReLU approximation results to softmax attention mechanism. This recipe covers many common approximation targets. Importantly, it yiel…
stat.ML2024
On Statistical Rates of Conditional Diffusion Transformers: Approximation, Estimation and Minimax Optimality
Jerry Yao-Chieh Hu, Weimin Wu, Yi-Chen Lee +3
We investigate the approximation and estimation rates of conditional diffusion transformers (DiTs) with classifier-free guidance. We present a comprehensive analysis for ``in-conte…