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]

🎉 Spotlight @ 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]

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]

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

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

📜 Arxiv Preprint 🗓 October 22, 2024 🔗 [paper]

Continual Learning

Convergence and Implicit Bias of Gradient Descent on Continual Linear Classification

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

📜 Under Review 🗓 November 16, 2024

🎉 Best Paper Award at JKAIA 2024

Convergence

Convergence and Implicit Bias of Gradient Descent on Continual Linear Classification

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

📜 Under Review 🗓 November 16, 2024

🎉 Best Paper Award at 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 Workshop on Advancing Neural Network Training (WANT)) 🗓 September 26, 2024 🔗 [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 Workshop on Advancing Neural Network Training (WANT)) 🗓 September 26, 2024 🔗 [paper]

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]

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 Workshop on Advancing Neural Network Training (WANT)) 🗓 September 26, 2024 🔗 [paper]

Gradient Descent

Convergence and Implicit Bias of Gradient Descent on Continual Linear Classification

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

📜 Under Review 🗓 November 16, 2024

🎉 Best Paper Award at 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]

🎉 Spotlight @ 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

📜 Under Review 🗓 November 16, 2024

🎉 Best Paper Award at 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 Workshop on Advancing Neural Network Training (WANT)) 🗓 September 26, 2024 🔗 [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]

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

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

📜 Arxiv Preprint 🗓 October 22, 2024 🔗 [paper]

Linear Classification

Convergence and Implicit Bias of Gradient Descent on Continual Linear Classification

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

📜 Under Review 🗓 November 16, 2024

🎉 Best Paper Award at 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 Workshop on Advancing Neural Network Training (WANT)) 🗓 September 26, 2024 🔗 [paper]

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]

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

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

📜 Arxiv Preprint 🗓 October 22, 2024 🔗 [paper]

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]

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]

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

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

📜 Arxiv Preprint 🗓 October 22, 2024 🔗 [paper]

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]

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

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

📜 Arxiv Preprint 🗓 October 22, 2024 🔗 [paper]

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]

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]

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]

SGDA

SGDA with shuffling: faster convergence for nonconvex-PŁ minimax optimization

👥 Hanseul Cho and Chulhee Yun

📜 ICLR 2023 🗓 February 02, 2023 🔗 [paper]

🎉 NAVER Outstanding Theory Paper Award at 2022 KAIA-NAVER Autumnal Joint Conference

Scratchpad

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

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

📜 Arxiv Preprint 🗓 October 22, 2024 🔗 [paper]

Sequential Learning

Convergence and Implicit Bias of Gradient Descent on Continual Linear Classification

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

📜 Under Review 🗓 November 16, 2024

🎉 Best Paper Award at 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]

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]

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]

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

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

📜 Arxiv Preprint 🗓 October 22, 2024 🔗 [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]

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 Workshop on Advancing Neural Network Training (WANT)) 🗓 September 26, 2024 🔗 [paper]

minimax optimization

SGDA with shuffling: faster convergence for nonconvex-PŁ minimax optimization

👥 Hanseul Cho and Chulhee Yun

📜 ICLR 2023 🗓 February 02, 2023 🔗 [paper]

🎉 NAVER Outstanding Theory Paper Award at 2022 KAIA-NAVER Autumnal Joint Conference

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]

🎉 Spotlight @ ICML 2024 (Top 3.5% among total submissions)

shuffling-based

SGDA with shuffling: faster convergence for nonconvex-PŁ minimax optimization

👥 Hanseul Cho and Chulhee Yun

📜 ICLR 2023 🗓 February 02, 2023 🔗 [paper]

🎉 NAVER Outstanding Theory Paper Award at 2022 KAIA-NAVER Autumnal Joint Conference

without-replacement sampling

SGDA with shuffling: faster convergence for nonconvex-PŁ minimax optimization

👥 Hanseul Cho and Chulhee Yun

📜 ICLR 2023 🗓 February 02, 2023 🔗 [paper]

🎉 NAVER Outstanding Theory Paper Award at 2022 KAIA-NAVER Autumnal Joint Conference