← Search

YinTat Lee

2 accepted papers

2022

Sampling with Riemannian Hamiltonian Monte Carlo in a Constrained Space

NeurIPS 2022accept

We demonstrate for the first time that ill-conditioned, non-smooth, constrained distributions in very high dimension, upwards of 100,000, can be sampled efficiently \emph{in practice}. Our algorithm incorporates constraints into the Riemannian version of Hamiltonian Monte Carlo and maintains sparsit…

2022

When Does Differentially Private Learning Not Suffer in High Dimensions?

NeurIPS 2022accept

Large pretrained models can be fine-tuned with differential privacy to achieve performance approaching that of non-private models. A common theme in these results is the surprising observation that high-dimensional models can achieve favorable privacy-utility trade-offs. This seemingly contradicts k…