6 papers
High-accuracy and dimension-free sampling with diffusions
Khashayar Gatmiry, Sitan Chen, Adil Salim
Diffusion models have shown remarkable empirical success in sampling from rich multi-modal distributions. Their inference relies on numerically solving a certain differential equat…
Sublinear iterations can suffice even for DDPMs
Matthew S. Zhang, Stephen Huan, Jerry Huang +3
SDE-based methods such as denoising diffusion probabilistic models (DDPMs) have shown remarkable success in real-world sample generation tasks. Prior analyses of DDPMs have been fo…
Quantum Probe Tomography
Sitan Chen, Jordan Cotler, Hsin-Yuan Huang
Characterizing quantum many-body systems is a fundamental problem across physics, chemistry, and materials science. While significant progress has been made, many existing Hamilton…
Blink of an eye: a simple theory for feature localization in generative models
Marvin Li, Aayush Karan, Sitan Chen
Large language models can exhibit unexpected behavior in the blink of an eye. In a recent computer use demo, a language model switched from coding to Googling pictures of Yellowsto…
Gradient dynamics for low-rank fine-tuning beyond kernels
Arif Kerem Dayi, Sitan Chen
LoRA has emerged as one of the de facto methods for fine-tuning foundation models with low computational cost and memory footprint. The idea is to only train a low-rank perturbatio…
What does guidance do? A fine-grained analysis in a simple setting
Muthu Chidambaram, Khashayar Gatmiry, Sitan Chen +2
The use of guidance in diffusion models was originally motivated by the premise that the guidance-modified score is that of the data distribution tilted by a conditional likelihood…