Search Results for author: Yoojin Jang

Found 3 papers, 1 papers with code

TopP&R: Robust Support Estimation Approach for Evaluating Fidelity and Diversity in Generative Models

1 code implementation NeurIPS 2023 Pum Jun Kim, Yoojin Jang, Jisu Kim, Jaejun Yoo

To the best of our knowledge, this is the first evaluation metric focused on the robust estimation of the support and provides its statistical consistency under noise.

Can We Find Strong Lottery Tickets in Generative Models?

no code implementations16 Dec 2022 Sangyeop Yeo, Yoojin Jang, Jy-yong Sohn, Dongyoon Han, Jaejun Yoo

To the best of our knowledge, we are the first to show the existence of strong lottery tickets in generative models and provide an algorithm to find it stably.

Model Compression Network Pruning

Best-response dynamics, playing sequences, and convergence to equilibrium in random games

no code implementations11 Jan 2021 Torsten Heinrich, Yoojin Jang, Luca Mungo, Marco Pangallo, Alex Scott, Bassel Tarbush, Samuel Wiese

By contrast, when the playing sequence is random, the dynamic converges to a pure Nash equilibrium if one exists in almost all (large) games.

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