Showing cs.LGShow all
2 papers · 1 filter
cs.LG2025
A solvable model of learning generative diffusion: theory and insights
Hugo Cui, Cengiz Pehlevan, Yue M. Lu
In this manuscript, we consider the problem of learning a flow or diffusion-based generative model parametrized by a two-layer auto-encoder, trained with online stochastic gradient…
cs.LG2025
High-Dimensional Analysis of Single-Layer Attention for Sparse-Token Classification
Nicholas Barnfield, Hugo Cui, Yue M. Lu
When and how can an attention mechanism learn to selectively attend to informative tokens, thereby enabling detection of weak, rare, and sparsely located features? We address these…