Search Results for author: Yuri Kinoshita

Found 3 papers, 1 papers with code

A provable control of sensitivity of neural networks through a direct parameterization of the overall bi-Lipschitzness

no code implementations15 Apr 2024 Yuri Kinoshita, Taro Toyoizumi

While neural networks can enjoy an outstanding flexibility and exhibit unprecedented performance, the mechanism behind their behavior is still not well-understood.

Inductive Bias

Controlling Posterior Collapse by an Inverse Lipschitz Constraint on the Decoder Network

no code implementations25 Apr 2023 Yuri Kinoshita, Kenta Oono, Kenji Fukumizu, Yuichi Yoshida, Shin-ichi Maeda

Variational autoencoders (VAEs) are one of the deep generative models that have experienced enormous success over the past decades.

Decoder

Improved Convergence Rate of Stochastic Gradient Langevin Dynamics with Variance Reduction and its Application to Optimization

1 code implementation30 Mar 2022 Yuri Kinoshita, Taiji Suzuki

The stochastic gradient Langevin Dynamics is one of the most fundamental algorithms to solve sampling problems and non-convex optimization appearing in several machine learning applications.

Cannot find the paper you are looking for? You can Submit a new open access paper.