Alert button
Picture for Chulhee Yun

Chulhee Yun

Alert button

Fundamental Benefit of Alternating Updates in Minimax Optimization

Feb 16, 2024
Jaewook Lee, Hanseul Cho, Chulhee Yun

Viaarxiv icon

Large Catapults in Momentum Gradient Descent with Warmup: An Empirical Study

Nov 25, 2023
Prin Phunyaphibarn, Junghyun Lee, Bohan Wang, Huishuai Zhang, Chulhee Yun

Figure 1 for Large Catapults in Momentum Gradient Descent with Warmup: An Empirical Study
Figure 2 for Large Catapults in Momentum Gradient Descent with Warmup: An Empirical Study
Figure 3 for Large Catapults in Momentum Gradient Descent with Warmup: An Empirical Study
Figure 4 for Large Catapults in Momentum Gradient Descent with Warmup: An Empirical Study
Viaarxiv icon

Fair Streaming Principal Component Analysis: Statistical and Algorithmic Viewpoint

Oct 28, 2023
Junghyun Lee, Hanseul Cho, Se-Young Yun, Chulhee Yun

Viaarxiv icon

Linear attention is (maybe) all you need (to understand transformer optimization)

Oct 02, 2023
Kwangjun Ahn, Xiang Cheng, Minhak Song, Chulhee Yun, Ali Jadbabaie, Suvrit Sra

Figure 1 for Linear attention is (maybe) all you need (to understand transformer optimization)
Figure 2 for Linear attention is (maybe) all you need (to understand transformer optimization)
Figure 3 for Linear attention is (maybe) all you need (to understand transformer optimization)
Figure 4 for Linear attention is (maybe) all you need (to understand transformer optimization)
Viaarxiv icon

Trajectory Alignment: Understanding the Edge of Stability Phenomenon via Bifurcation Theory

Jul 09, 2023
Minhak Song, Chulhee Yun

Figure 1 for Trajectory Alignment: Understanding the Edge of Stability Phenomenon via Bifurcation Theory
Figure 2 for Trajectory Alignment: Understanding the Edge of Stability Phenomenon via Bifurcation Theory
Figure 3 for Trajectory Alignment: Understanding the Edge of Stability Phenomenon via Bifurcation Theory
Figure 4 for Trajectory Alignment: Understanding the Edge of Stability Phenomenon via Bifurcation Theory
Viaarxiv icon

Practical Sharpness-Aware Minimization Cannot Converge All the Way to Optima

Jun 26, 2023
Dongkuk Si, Chulhee Yun

Figure 1 for Practical Sharpness-Aware Minimization Cannot Converge All the Way to Optima
Figure 2 for Practical Sharpness-Aware Minimization Cannot Converge All the Way to Optima
Figure 3 for Practical Sharpness-Aware Minimization Cannot Converge All the Way to Optima
Figure 4 for Practical Sharpness-Aware Minimization Cannot Converge All the Way to Optima
Viaarxiv icon

Enhancing Generalization and Plasticity for Sample Efficient Reinforcement Learning

Jun 19, 2023
Hojoon Lee, Hanseul Cho, Hyunseung Kim, Daehoon Gwak, Joonkee Kim, Jaegul Choo, Se-Young Yun, Chulhee Yun

Viaarxiv icon

Provable Benefit of Mixup for Finding Optimal Decision Boundaries

Jun 06, 2023
Junsoo Oh, Chulhee Yun

Figure 1 for Provable Benefit of Mixup for Finding Optimal Decision Boundaries
Figure 2 for Provable Benefit of Mixup for Finding Optimal Decision Boundaries
Figure 3 for Provable Benefit of Mixup for Finding Optimal Decision Boundaries
Figure 4 for Provable Benefit of Mixup for Finding Optimal Decision Boundaries
Viaarxiv icon

Tighter Lower Bounds for Shuffling SGD: Random Permutations and Beyond

Mar 13, 2023
Jaeyoung Cha, Jaewook Lee, Chulhee Yun

Figure 1 for Tighter Lower Bounds for Shuffling SGD: Random Permutations and Beyond
Viaarxiv icon