Taeho Yoon

activity

20212026

most citedAccelerated Algorithms for Smooth Convex-Concave Minimax Problems with

O (1/ k^{2})

Rate on Squared Gradient Norm

8 citations · 14 across the 9 of their papers we have counts for

collaborators

Showing 2021Show all

2 papers · 1 filter

math.OC2021★ 8 cited

Accelerated Algorithms for Smooth Convex-Concave Minimax Problems with $O (1/ k^{2})$ Rate on Squared Gradient Norm

TaeHo Yoon, Ernest K. Ryu

In this work, we study the computational complexity of reducing the squared gradient magnitude for smooth minimax optimization problems. First, we present algorithms with accelerat…

cs.LG2021

WGAN with an Infinitely Wide Generator Has No Spurious Stationary Points

Albert No, TaeHo Yoon, Sehyun Kwon +1

Generative adversarial networks (GAN) are a widely used class of deep generative models, but their minimax training dynamics are not understood very well. In this work, we show tha…

Accelerated Algorithms for Smooth Convex-Concave Minimax Problems with O(1/k2) Rate on Squared Gradient Norm

WGAN with an Infinitely Wide Generator Has No Spurious Stationary Points

Accelerated Algorithms for Smooth Convex-Concave Minimax Problems with $O (1/ k^{2})$ Rate on Squared Gradient Norm