24 citations · 24 across the 3 of their papers we have counts for
4 papers
Alternating Diffusion for Proximal Sampling with Zeroth Order Queries
Hirohane Takagi, Atsushi Nitanda
This work introduces a new approximate proximal sampler that operates solely with zeroth-order information of the potential function. Prior theoretical analyses have revealed that…
Uniform-in- log-Sobolev inequality for the mean-field Langevin dynamics with convex energy
Sinho Chewi, Atsushi Nitanda, Matthew S. Zhang
We establish a log-Sobolev inequality for the stationary distribution of mean-field Langevin dynamics with a constant that is independent of the number of particles . Our proof…
Why is parameter averaging beneficial in SGD? An objective smoothing perspective
Atsushi Nitanda, Ryuhei Kikuchi, Shugo Maeda +1
It is often observed that stochastic gradient descent (SGD) and its variants implicitly select a solution with good generalization performance; such implicit bias is often characte…
Data Cleansing for Models Trained with SGD
Satoshi Hara, Atsushi Nitanda, Takanori Maehara
Data cleansing is a typical approach used to improve the accuracy of machine learning models, which, however, requires extensive domain knowledge to identify the influential instan…