Publications by Tags

Alex-GDA

Fundamental Benefit of Alternating Updates in Minimax Optimization

👥 Jaewook Lee*, Hanseul Cho*, and Chulhee Yun

📰 ICML 2024 (Short version at ICLR 2024 Workshop on Bridging the Gap Between Practice and Theory in Deep Learning (BGPT)) 🗓 May 02, 2024

🔗 [paper] [arxiv] [LinkedIn]

🎉 Spotlight at the 41st Int'l Conf. on Machine Learning (ICML 2024; Top 3.5% among total submissions)

Algorithmic Tasks

Position Coupling: Improving Length Generalization of Arithmetic Transformers Using Task Structure

👥 Hanseul Cho*, Jaeyoung Cha*, Pranjal Awasthi, Srinadh Bhojanapalli, Anupam Gupta, and Chulhee Yun

📰 NeurIPS 2024 (Short version at ICML 2024 Workshop on Long-Context Foundation Models (LCFM)) 🗓 September 26, 2024

🔗 [paper] [arxiv] [LinkedIn]

Arithmetic Tasks

Position Coupling: Improving Length Generalization of Arithmetic Transformers Using Task Structure

👥 Hanseul Cho*, Jaeyoung Cha*, Pranjal Awasthi, Srinadh Bhojanapalli, Anupam Gupta, and Chulhee Yun

📰 NeurIPS 2024 (Short version at ICML 2024 Workshop on Long-Context Foundation Models (LCFM)) 🗓 September 26, 2024

🔗 [paper] [arxiv] [LinkedIn]

Arithmetic Transformers Can Length-Generalize in Both Operand Length and Count

👥 Hanseul Cho*, Jaeyoung Cha*, Srinadh Bhojanapalli, and Chulhee Yun

📰 ICLR 2025 🗓 January 23, 2025

🔗 [paper] [arxiv] [X (Twitter)] [LinkedIn]

Continual Learning

Convergence and Implicit Bias of Gradient Descent on Continual Linear Classification

👥 Hyunji Jung*, Hanseul Cho*, and Chulhee Yun

📰 ICLR 2025 🗓 January 23, 2025

🔗 [paper] [arxiv]

🎉 Best Paper Award at the 11th Joint Conference of Korean Artificial Intelligence Association (JKAIA 2024)

Convergence

Convergence and Implicit Bias of Gradient Descent on Continual Linear Classification

👥 Hyunji Jung*, Hanseul Cho*, and Chulhee Yun

📰 ICLR 2025 🗓 January 23, 2025

🔗 [paper] [arxiv]

🎉 Best Paper Award at the 11th Joint Conference of Korean Artificial Intelligence Association (JKAIA 2024)

DASH

DASH: Warm-Starting Neural Network Training in Stationary Settings without Loss of Plasticity

👥 Baekrok Shin*, Junsoo Oh*, Hanseul Cho, and Chulhee Yun

📰 NeurIPS 2024 (Short version at ICML 2024 Workshop on Advancing Neural Network Training (WANT)) 🗓 September 26, 2024

🔗 [paper] [arxiv]

Deep Model-Based Optimization

Deep Model-Based Optimization of Jamming Effectiveness under Aircraft AESA Radar Operational Environments [KOR]

👥 Hanseul Cho, Baekrok Shin, Chaewon Moon, Sang-Geun Hong, U-Ju Byeon, Jin-Yong Sung, and Chulhee Yun

📰 Journal of Kor. Inst. of Comm & Info. Sci. (J-KICS) 🗓 November 15, 2025

🔗 [paper]

Direction-Aware SHrinking

DASH: Warm-Starting Neural Network Training in Stationary Settings without Loss of Plasticity

👥 Baekrok Shin*, Junsoo Oh*, Hanseul Cho, and Chulhee Yun

📰 NeurIPS 2024 (Short version at ICML 2024 Workshop on Advancing Neural Network Training (WANT)) 🗓 September 26, 2024

🔗 [paper] [arxiv]

Fairness

Fair Streaming Principal Component Analysis: Statistical and Algorithmic Viewpoint

👥 Junghyun Lee*, Hanseul Cho*, Se-Young Yun, and Chulhee Yun

📰 NeurIPS 2023 🗓 September 22, 2023

🔗 [paper] [arxiv] [X (Twitter)]

Generalization

DASH: Warm-Starting Neural Network Training in Stationary Settings without Loss of Plasticity

👥 Baekrok Shin*, Junsoo Oh*, Hanseul Cho, and Chulhee Yun

📰 NeurIPS 2024 (Short version at ICML 2024 Workshop on Advancing Neural Network Training (WANT)) 🗓 September 26, 2024

🔗 [paper] [arxiv]

Gradient Descent

Convergence and Implicit Bias of Gradient Descent on Continual Linear Classification

👥 Hyunji Jung*, Hanseul Cho*, and Chulhee Yun

📰 ICLR 2025 🗓 January 23, 2025

🔗 [paper] [arxiv]

🎉 Best Paper Award at the 11th Joint Conference of Korean Artificial Intelligence Association (JKAIA 2024)

Gradient Descent-Ascent (GDA)

Fundamental Benefit of Alternating Updates in Minimax Optimization

👥 Jaewook Lee*, Hanseul Cho*, and Chulhee Yun

📰 ICML 2024 (Short version at ICLR 2024 Workshop on Bridging the Gap Between Practice and Theory in Deep Learning (BGPT)) 🗓 May 02, 2024

🔗 [paper] [arxiv] [LinkedIn]

🎉 Spotlight at the 41st Int'l Conf. on Machine Learning (ICML 2024; Top 3.5% among total submissions)

Implicit Bias

Convergence and Implicit Bias of Gradient Descent on Continual Linear Classification

👥 Hyunji Jung*, Hanseul Cho*, and Chulhee Yun

📰 ICLR 2025 🗓 January 23, 2025

🔗 [paper] [arxiv]

🎉 Best Paper Award at the 11th Joint Conference of Korean Artificial Intelligence Association (JKAIA 2024)

Incremental Learning

DASH: Warm-Starting Neural Network Training in Stationary Settings without Loss of Plasticity

👥 Baekrok Shin*, Junsoo Oh*, Hanseul Cho, and Chulhee Yun

📰 NeurIPS 2024 (Short version at ICML 2024 Workshop on Advancing Neural Network Training (WANT)) 🗓 September 26, 2024

🔗 [paper] [arxiv]

Korean-only

Deep Model-Based Optimization of Jamming Effectiveness under Aircraft AESA Radar Operational Environments [KOR]

👥 Hanseul Cho, Baekrok Shin, Chaewon Moon, Sang-Geun Hong, U-Ju Byeon, Jin-Yong Sung, and Chulhee Yun

📰 Journal of Kor. Inst. of Comm & Info. Sci. (J-KICS) 🗓 November 15, 2025

🔗 [paper]

LV

Layer Verification Accelerates Speculative Tree Decoding

👥 Jaeyoung Cha*, Hanseul Cho*, and Chulhee Yun

📰 AdaptFM @ ICML2026 🗓 July 11, 2026

🔗 [paper]

Layer Verification

Layer Verification Accelerates Speculative Tree Decoding

👥 Jaeyoung Cha*, Hanseul Cho*, and Chulhee Yun

📰 AdaptFM @ ICML2026 🗓 July 11, 2026

🔗 [paper]

Length Generalization

Position Coupling: Improving Length Generalization of Arithmetic Transformers Using Task Structure

👥 Hanseul Cho*, Jaeyoung Cha*, Pranjal Awasthi, Srinadh Bhojanapalli, Anupam Gupta, and Chulhee Yun

📰 NeurIPS 2024 (Short version at ICML 2024 Workshop on Long-Context Foundation Models (LCFM)) 🗓 September 26, 2024

🔗 [paper] [arxiv] [LinkedIn]

Arithmetic Transformers Can Length-Generalize in Both Operand Length and Count

👥 Hanseul Cho*, Jaeyoung Cha*, Srinadh Bhojanapalli, and Chulhee Yun

📰 ICLR 2025 🗓 January 23, 2025

🔗 [paper] [arxiv] [X (Twitter)] [LinkedIn]

Linear Classification

Convergence and Implicit Bias of Gradient Descent on Continual Linear Classification

👥 Hyunji Jung*, Hanseul Cho*, and Chulhee Yun

📰 ICLR 2025 🗓 January 23, 2025

🔗 [paper] [arxiv]

🎉 Best Paper Award at the 11th Joint Conference of Korean Artificial Intelligence Association (JKAIA 2024)

Loss of Plasticity

DASH: Warm-Starting Neural Network Training in Stationary Settings without Loss of Plasticity

👥 Baekrok Shin*, Junsoo Oh*, Hanseul Cho, and Chulhee Yun

📰 NeurIPS 2024 (Short version at ICML 2024 Workshop on Advancing Neural Network Training (WANT)) 🗓 September 26, 2024

🔗 [paper] [arxiv]

Out-of-distribution Generalization

Position Coupling: Improving Length Generalization of Arithmetic Transformers Using Task Structure

👥 Hanseul Cho*, Jaeyoung Cha*, Pranjal Awasthi, Srinadh Bhojanapalli, Anupam Gupta, and Chulhee Yun

📰 NeurIPS 2024 (Short version at ICML 2024 Workshop on Long-Context Foundation Models (LCFM)) 🗓 September 26, 2024

🔗 [paper] [arxiv] [LinkedIn]

Arithmetic Transformers Can Length-Generalize in Both Operand Length and Count

👥 Hanseul Cho*, Jaeyoung Cha*, Srinadh Bhojanapalli, and Chulhee Yun

📰 ICLR 2025 🗓 January 23, 2025

🔗 [paper] [arxiv] [X (Twitter)] [LinkedIn]

Plasticity

PLASTIC: Improving Input and Label Plasticity for Sample Efficient Reinforcement Learning

👥 Hojoon Lee*, Hanseul Cho*, Hyunseung Kim*, Daehoon Gwak, Joonkee Kim, Jaegul Choo, Se-Young Yun, and Chulhee Yun

📰 NeurIPS 2023 🗓 September 22, 2023

🔗 [paper] [arxiv]

Poissonization

Characterizing Pattern Matching and Its Limits on Compositional Task Structures

👥 Hoyeon Chang*, Jinho Park*, Hanseul Cho*, Sohee Yang, Miyoung Ko, Hyeonbin Hwang, Seungpil Won, Dohaeng Lee, Youbin Ahn, and Minjoon Seo

📰 ICLR 2026 🗓 January 26, 2026

🔗 [paper] [arxiv] [X (Twitter)]

Position Coupling

Position Coupling: Improving Length Generalization of Arithmetic Transformers Using Task Structure

👥 Hanseul Cho*, Jaeyoung Cha*, Pranjal Awasthi, Srinadh Bhojanapalli, Anupam Gupta, and Chulhee Yun

📰 NeurIPS 2024 (Short version at ICML 2024 Workshop on Long-Context Foundation Models (LCFM)) 🗓 September 26, 2024

🔗 [paper] [arxiv] [LinkedIn]

Arithmetic Transformers Can Length-Generalize in Both Operand Length and Count

👥 Hanseul Cho*, Jaeyoung Cha*, Srinadh Bhojanapalli, and Chulhee Yun

📰 ICLR 2025 🗓 January 23, 2025

🔗 [paper] [arxiv] [X (Twitter)] [LinkedIn]

Positional Encoding

Position Coupling: Improving Length Generalization of Arithmetic Transformers Using Task Structure

👥 Hanseul Cho*, Jaeyoung Cha*, Pranjal Awasthi, Srinadh Bhojanapalli, Anupam Gupta, and Chulhee Yun

📰 NeurIPS 2024 (Short version at ICML 2024 Workshop on Long-Context Foundation Models (LCFM)) 🗓 September 26, 2024

🔗 [paper] [arxiv] [LinkedIn]

Arithmetic Transformers Can Length-Generalize in Both Operand Length and Count

👥 Hanseul Cho*, Jaeyoung Cha*, Srinadh Bhojanapalli, and Chulhee Yun

📰 ICLR 2025 🗓 January 23, 2025

🔗 [paper] [arxiv] [X (Twitter)] [LinkedIn]

Principal Component Analysis (PCA)

Fair Streaming Principal Component Analysis: Statistical and Algorithmic Viewpoint

👥 Junghyun Lee*, Hanseul Cho*, Se-Young Yun, and Chulhee Yun

📰 NeurIPS 2023 🗓 September 22, 2023

🔗 [paper] [arxiv] [X (Twitter)]

Radar Jamming

Deep Model-Based Optimization of Jamming Effectiveness under Aircraft AESA Radar Operational Environments [KOR]

👥 Hanseul Cho, Baekrok Shin, Chaewon Moon, Sang-Geun Hong, U-Ju Byeon, Jin-Yong Sung, and Chulhee Yun

📰 Journal of Kor. Inst. of Comm & Info. Sci. (J-KICS) 🗓 November 15, 2025

🔗 [paper]

Reinforcement Learning

PLASTIC: Improving Input and Label Plasticity for Sample Efficient Reinforcement Learning

👥 Hojoon Lee*, Hanseul Cho*, Hyunseung Kim*, Daehoon Gwak, Joonkee Kim, Jaegul Choo, Se-Young Yun, and Chulhee Yun

📰 NeurIPS 2023 🗓 September 22, 2023

🔗 [paper] [arxiv]

Reset Mechanism

PLASTIC: Improving Input and Label Plasticity for Sample Efficient Reinforcement Learning

👥 Hojoon Lee*, Hanseul Cho*, Hyunseung Kim*, Daehoon Gwak, Joonkee Kim, Jaegul Choo, Se-Young Yun, and Chulhee Yun

📰 NeurIPS 2023 🗓 September 22, 2023

🔗 [paper] [arxiv]

SGDA

SGDA with Shuffling: Faster Convergence For Nonconvex-PŁ Minimax Optimization

👥 Hanseul Cho and Chulhee Yun

📰 ICLR 2023 🗓 February 02, 2023

🔗 [paper] [arxiv]

🎉 NAVER Outstanding Theory Paper Award at the 7th Joint Conference of Korea Artificial Intelligence Association (JKAIA 2022)

Scratchpad

Arithmetic Transformers Can Length-Generalize in Both Operand Length and Count

👥 Hanseul Cho*, Jaeyoung Cha*, Srinadh Bhojanapalli, and Chulhee Yun

📰 ICLR 2025 🗓 January 23, 2025

🔗 [paper] [arxiv] [X (Twitter)] [LinkedIn]

Sequential Learning

Convergence and Implicit Bias of Gradient Descent on Continual Linear Classification

👥 Hyunji Jung*, Hanseul Cho*, and Chulhee Yun

📰 ICLR 2025 🗓 January 23, 2025

🔗 [paper] [arxiv]

🎉 Best Paper Award at the 11th Joint Conference of Korean Artificial Intelligence Association (JKAIA 2024)

Sharpness-aware Minimization

PLASTIC: Improving Input and Label Plasticity for Sample Efficient Reinforcement Learning

👥 Hojoon Lee*, Hanseul Cho*, Hyunseung Kim*, Daehoon Gwak, Joonkee Kim, Jaegul Choo, Se-Young Yun, and Chulhee Yun

📰 NeurIPS 2023 🗓 September 22, 2023

🔗 [paper] [arxiv]

Speculative Decoding

Layer Verification Accelerates Speculative Tree Decoding

👥 Jaeyoung Cha*, Hanseul Cho*, and Chulhee Yun

📰 AdaptFM @ ICML2026 🗓 July 11, 2026

🔗 [paper]

Streaming

Fair Streaming Principal Component Analysis: Statistical and Algorithmic Viewpoint

👥 Junghyun Lee*, Hanseul Cho*, Se-Young Yun, and Chulhee Yun

📰 NeurIPS 2023 🗓 September 22, 2023

🔗 [paper] [arxiv] [X (Twitter)]

Transformers

Position Coupling: Improving Length Generalization of Arithmetic Transformers Using Task Structure

👥 Hanseul Cho*, Jaeyoung Cha*, Pranjal Awasthi, Srinadh Bhojanapalli, Anupam Gupta, and Chulhee Yun

📰 NeurIPS 2024 (Short version at ICML 2024 Workshop on Long-Context Foundation Models (LCFM)) 🗓 September 26, 2024

🔗 [paper] [arxiv] [LinkedIn]

Arithmetic Transformers Can Length-Generalize in Both Operand Length and Count

👥 Hanseul Cho*, Jaeyoung Cha*, Srinadh Bhojanapalli, and Chulhee Yun

📰 ICLR 2025 🗓 January 23, 2025

🔗 [paper] [arxiv] [X (Twitter)] [LinkedIn]

Tree Speculative Decoding

Layer Verification Accelerates Speculative Tree Decoding

👥 Jaeyoung Cha*, Hanseul Cho*, and Chulhee Yun

📰 AdaptFM @ ICML2026 🗓 July 11, 2026

🔗 [paper]

Unsupervised Learnability

Fair Streaming Principal Component Analysis: Statistical and Algorithmic Viewpoint

👥 Junghyun Lee*, Hanseul Cho*, Se-Young Yun, and Chulhee Yun

📰 NeurIPS 2023 🗓 September 22, 2023

🔗 [paper] [arxiv] [X (Twitter)]

Warm-Starting

DASH: Warm-Starting Neural Network Training in Stationary Settings without Loss of Plasticity

👥 Baekrok Shin*, Junsoo Oh*, Hanseul Cho, and Chulhee Yun

📰 NeurIPS 2024 (Short version at ICML 2024 Workshop on Advancing Neural Network Training (WANT)) 🗓 September 26, 2024

🔗 [paper] [arxiv]

compositional generalization

Characterizing Pattern Matching and Its Limits on Compositional Task Structures

👥 Hoyeon Chang*, Jinho Park*, Hanseul Cho*, Sohee Yang, Miyoung Ko, Hyeonbin Hwang, Seungpil Won, Dohaeng Lee, Youbin Ahn, and Minjoon Seo

📰 ICLR 2026 🗓 January 26, 2026

🔗 [paper] [arxiv] [X (Twitter)]

coverage

Characterizing Pattern Matching and Its Limits on Compositional Task Structures

👥 Hoyeon Chang*, Jinho Park*, Hanseul Cho*, Sohee Yang, Miyoung Ko, Hyeonbin Hwang, Seungpil Won, Dohaeng Lee, Youbin Ahn, and Minjoon Seo

📰 ICLR 2026 🗓 January 26, 2026

🔗 [paper] [arxiv] [X (Twitter)]

minimax optimization

SGDA with Shuffling: Faster Convergence For Nonconvex-PŁ Minimax Optimization

👥 Hanseul Cho and Chulhee Yun

📰 ICLR 2023 🗓 February 02, 2023

🔗 [paper] [arxiv]

🎉 NAVER Outstanding Theory Paper Award at the 7th Joint Conference of Korea Artificial Intelligence Association (JKAIA 2022)

Fundamental Benefit of Alternating Updates in Minimax Optimization

👥 Jaewook Lee*, Hanseul Cho*, and Chulhee Yun

📰 ICML 2024 (Short version at ICLR 2024 Workshop on Bridging the Gap Between Practice and Theory in Deep Learning (BGPT)) 🗓 May 02, 2024

🔗 [paper] [arxiv] [LinkedIn]

🎉 Spotlight at the 41st Int'l Conf. on Machine Learning (ICML 2024; Top 3.5% among total submissions)

pattern matching

Characterizing Pattern Matching and Its Limits on Compositional Task Structures

👥 Hoyeon Chang*, Jinho Park*, Hanseul Cho*, Sohee Yang, Miyoung Ko, Hyeonbin Hwang, Seungpil Won, Dohaeng Lee, Youbin Ahn, and Minjoon Seo

📰 ICLR 2026 🗓 January 26, 2026

🔗 [paper] [arxiv] [X (Twitter)]

random graph theory

Characterizing Pattern Matching and Its Limits on Compositional Task Structures

👥 Hoyeon Chang*, Jinho Park*, Hanseul Cho*, Sohee Yang, Miyoung Ko, Hyeonbin Hwang, Seungpil Won, Dohaeng Lee, Youbin Ahn, and Minjoon Seo

📰 ICLR 2026 🗓 January 26, 2026

🔗 [paper] [arxiv] [X (Twitter)]

random intersection graph

Characterizing Pattern Matching and Its Limits on Compositional Task Structures

👥 Hoyeon Chang*, Jinho Park*, Hanseul Cho*, Sohee Yang, Miyoung Ko, Hyeonbin Hwang, Seungpil Won, Dohaeng Lee, Youbin Ahn, and Minjoon Seo

📰 ICLR 2026 🗓 January 26, 2026

🔗 [paper] [arxiv] [X (Twitter)]

shuffling-based

SGDA with Shuffling: Faster Convergence For Nonconvex-PŁ Minimax Optimization

👥 Hanseul Cho and Chulhee Yun

📰 ICLR 2023 🗓 February 02, 2023

🔗 [paper] [arxiv]

🎉 NAVER Outstanding Theory Paper Award at the 7th Joint Conference of Korea Artificial Intelligence Association (JKAIA 2022)

without-replacement sampling

SGDA with Shuffling: Faster Convergence For Nonconvex-PŁ Minimax Optimization

👥 Hanseul Cho and Chulhee Yun

📰 ICLR 2023 🗓 February 02, 2023

🔗 [paper] [arxiv]

🎉 NAVER Outstanding Theory Paper Award at the 7th Joint Conference of Korea Artificial Intelligence Association (JKAIA 2022)

Hanseul Cho (조한슬)

Publications by Tags

Alex-GDA

Algorithmic Tasks

Arithmetic Tasks

Continual Learning

Convergence

DASH

Deep Model-Based Optimization

Direction-Aware SHrinking

Fairness

Generalization

Gradient Descent

Gradient Descent-Ascent (GDA)

Implicit Bias

Incremental Learning

Korean-only

LV

Layer Verification

Length Generalization

Linear Classification

Loss of Plasticity

Out-of-distribution Generalization

Plasticity

Poissonization

Position Coupling

Positional Encoding

Principal Component Analysis (PCA)

Radar Jamming

Reinforcement Learning

Reset Mechanism

SGDA

Scratchpad

Sequential Learning

Sharpness-aware Minimization

Speculative Decoding

Streaming

Transformers

Tree Speculative Decoding

Unsupervised Learnability

Warm-Starting

compositional generalization

coverage

minimax optimization

pattern matching

random graph theory

random intersection graph

shuffling-based

without-replacement sampling