5 papers
On importance sampling and independent Metropolis-Hastings with an unbounded weight function
George Deligiannidis, Pierre E. Jacob, El Mahdi Khribch +1
Importance sampling and independent Metropolis-Hastings are among the fundamental building blocks of Monte Carlo methods. Both require a proposal distribution that globally approxi…
Couple to Control: Joint Initial Noise Design in Diffusion Models
Jing Jia, Liyue Shen, Guanyang Wang
Diffusion models typically generate image batches from independent Gaussian initial noises. We argue that this independence assumption is only one choice within a broader class of…
Differentially Private Range Queries with Correlated Input Perturbation
Prathamesh Dharangutte, Jie Gao, Ruobin Gong +1
This work proposes a class of differentially private mechanisms for linear queries, in particular range queries, that leverages correlated input perturbation to simultaneously achi…
A phase transition in sampling from Restricted Boltzmann Machines
Youngwoo Kwon, Qian Qin, Guanyang Wang +1
Restricted Boltzmann Machines are a class of undirected graphical models that play a key role in deep learning and unsupervised learning. In this study, we prove a phase transition…
Putting all eggs in one basket: some insights from a correlation inequality
Pradeep Dubey, Siddhartha Sahi, Guanyang Wang
We give examples of situations -- stochastic production, military tactics, corporate merger -- where it is beneficial to concentrate risk rather than to diversify it, that is, to p…