3 papers
cs.LG2026
Why Are DMD Students Lazy? Understanding the Copying Behavior in Few-Step Distillation
Shucheng Li, Iolo Jones, Alexander Tong +1
Distribution Matching Distillation (DMD) compresses pretrained diffusion models into efficient few-step generators by aligning their noised distributions across all scales. In prin…
cs.DS2026
Learning Mixture Models via Efficient High-dimensional Sparse Fourier Transforms
Alkis Kalavasis, Pravesh K. Kothari, Shuchen Li +1
In this work, we give a time and sample algorithm for efficiently learning the parameters of a mixture of spherical distributions in dimensions. Unlike al…
cs.LG2024
On the Hardness of Learning One Hidden Layer Neural Networks
Shuchen Li, Ilias Zadik, Manolis Zampetakis
In this work, we consider the problem of learning one hidden layer ReLU neural networks with inputs from . We show that this learning problem is hard under standard c…