TaeHo Yoon

TaeHo Yoon

I'm a Research Scientist at Johns Hopkins University,
Department of Applied Mathematics & Statistics.
I study optimization and theoretical aspects of machine learning.

List of Publications

Dual-Anchor Acceleration Is Near-Optimal for Stochastic Monotone Root-Finding

TaeHo Yoon, Nicolas Loizou

optimization stochastic-optimization root-finding-problems acceleration dual-anchoring

Anchored Extra-Proximal Methods: Optimal Higher-Order Methods for Monotone Inclusion Problems

Ruichen Jiang, TaeHo Yoon

optimization monotone-inclusions higher-order-methods acceleration oracle-complexity

Polyak-Type Extragradient Methods for Monotone Root-Finding Problems

TaeHo Yoon, Sayantan Choudhury, Ezra Greenberg, Nicolas Loizou

optimization stochastic-optimization root-finding-problems extragradient Polyak-step-sizes

Direct Acceleration of Stochastic Root-Finding Without Variance Reduction and Regularization

TaeHo Yoon, Nicolas Loizou

optimization stochastic-optimization root-finding-problems acceleration

On Same-Sample and Independent-Sample Stochastic Extragradient for Monotone Variational Inequalities

TaeHo Yoon, Nicolas Loizou

stochastic-optimization variational-inequalities extragradient

Peppy: An AI-Assisted Workflow for Tight Convergence Analysis of Optimization Algorithms

Jaewook J. Suh, TaeHo Yoon, Edward D. H. Nguyen, Bicheng Ying, Shiqian Ma

optimization AI-assisted-research convergence-analysis lyapunov-analysis

Toward a Systematic Understanding and Interactive Search of Lyapunov-Style Proofs in Optimization

TaeHo Yoon, Jaewook J. Suh, Edward Duc Hien Nguyen, Bicheng Ying, Shiqian Ma

optimization performance-estimation lyapunov-analysis tight-proofs

A Theory of Composition and Duality of Extremal Optimal Fixed-Point Algorithms

TaeHo Yoon, Benjamin Grimmer

optimization acceleration fixed-point-problems H-duality

H-invariance Theory: A Complete Characterization of Minimax Optimal Fixed-Point Algorithms

TaeHo Yoon, Ernest K. Ryu, Benjamin Grimmer

optimization acceleration fixed-point-problems

Multiplayer Federated Learning: Reaching Equilibrium with Less Communication

TaeHo Yoon, Sayantan Choudhury, Nicolas Loizou

optimization federated-learning multiplayer-game-theory

Optimal Acceleration for Minimax and Fixed-Point Problems is Not Unique

TaeHo Yoon, Jaeyeon Kim, Jaewook J. Suh, Ernest K. Ryu

optimization minimax-optimization fixed-point acceleration H-duality

Censored Sampling of Diffusion Models Using 3 Minutes of Human Feedback

TaeHo Yoon, Kibeom Myoung, Keon Lee, Jaewoong Cho, Albert No and Ernest K. Ryu

generative-models diffusion-models controlled-generation RLHF

Diffusion Probabilistic Models Generalize when They Fail to Memorize

TaeHo Yoon, Joo Young Choi, Sehyun Kwon and Ernest K. Ryu

generative-models diffusion-models generalization

Accelerated Minimax Algorithms Flock Together

TaeHo Yoon and Ernest K. Ryu

optimization minimax-optimization acceleration

Robust Probabilistic Time Series Forecasting

TaeHo Yoon, Youngsuk Park, Ernest K. Ryu and Yuyang Wang

probabilistic-forecasting time-series adversarial-robustness

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

TaeHo Yoon and Ernest K. Ryu

optimization minimax-optimization acceleration

WGAN with an Infinitely Wide Generator Has No Spurious Stationary Points

Albert No, TaeHo Yoon, Sehyun Kwon and Ernest K. Ryu

generative-models GANs infinite-neural-networks