3 citations · 4 across the 3 of their papers we have counts for
3 papers
stat.ML2024
Top-Down Bayesian Posterior Sampling for Sum-Product Networks
Soma Yokoi, Issei Sato
Sum-product networks (SPNs) are probabilistic models characterized by exact and fast evaluation of fundamental probabilistic operations. Its superior computational tractability has…
stat.ML2019★ 3 cited
Bayesian interpretation of SGD as Ito process
Soma Yokoi, Issei Sato
The current interpretation of stochastic gradient descent (SGD) as a stochastic process lacks generality in that its numerical scheme restricts continuous-time dynamics as well as…
stat.ML2019★ 1 cited
On Transformations in Stochastic Gradient MCMC
Soma Yokoi, Takuma Otsuka, Issei Sato
Stochastic gradient Langevin dynamics (SGLD) is a computationally efficient sampler for Bayesian posterior inference given a large scale dataset. Although SGLD is designed for unbo…