6 papers
VGB for Masked Diffusion Model: Efficient Test-time Scaling for Reward Satisfaction and Sample Editing
Kijung Jeon, Thuy-Duong Vuong, Molei Tao
Inference-time scaling is a promising paradigm to improve generative models, especially when outputs must satisfy structural constraints or optimize downstream rewards. We consider…
A computational phase transition for learning-to-sample from Ising models
Andrej Risteski, Thuy-Duong Vuong
We study \emph{learning-to-sample} -- a basic algorithmic task underlying generative modeling -- for Ising models, a standard testbed for algorithmic ideas in both theoretical comp…
Entropic independence via sparse localization
Vishesh Jain, Huy Tuan Pham, Thuy-Duong Vuong
Entropic independence is a structural property of measures that underlies modern proofs of functional inequalities, notably (modified) log-Sobolev inequalities, via ``annealing'' o…
Parallel Sampling via Autospeculation
Nima Anari, Carlo Baronio, CJ Chen +4
We present parallel algorithms to accelerate sampling via counting in two settings: any-order autoregressive models and denoising diffusion models. An any-order autoregressive mode…
On quantum to classical comparison for Davies generators
Joao Basso, Shirshendu Ganguly, Alistair Sinclair +3
Despite extensive study, our understanding of quantum Markov chains remains far less complete than that of their classical counterparts. [Temme'13] observed that the Davies Lindbla…
Composable Coresets for Constrained Determinant Maximization and Beyond
Sepideh Mahabadi, Thuy-Duong Vuong
We study algorithms for construction of composable coresets for the task of Determinant Maximization under partition constraint. Given a point set that is p…