Chulhee Yun

Publication Activity (10 Years)

Years Active: 2013-2024
Publications (10 Years): 50

Top Topics

Global Optimality

Set Of Randomly Generated Instances

Top Venues

Publications

Kwangjun Ahn, Xiang Cheng, Minhak Song, Chulhee Yun, Ali Jadbabaie, Suvrit Sra
Linear attention is (maybe) all you need (to understand Transformer optimization). ICLR (2024)
Minhak Song, Kwangjun Ahn, Chulhee Yun
Does SGD really happen in tiny subspaces? CoRR (2024)
Jaewook Lee, Hanseul Cho, Chulhee Yun
Fundamental Benefit of Alternating Updates in Minimax Optimization. CoRR (2024)
Hanseul Cho, Jaeyoung Cha, Pranjal Awasthi, Srinadh Bhojanapalli, Anupam Gupta, Chulhee Yun
Position Coupling: Leveraging Task Structure for Improved Length Generalization of Transformers. CoRR (2024)
Hojoon Lee, Hanseul Cho, Hyunseung Kim, Daehoon Gwak, Joonkee Kim, Jaegul Choo, Se-Young Yun, Chulhee Yun
Enhancing Generalization and Plasticity for Sample Efficient Reinforcement Learning. CoRR (2023)
Junghyun Lee, Hanseul Cho, Se-Young Yun, Chulhee Yun
Fair Streaming Principal Component Analysis: Statistical and Algorithmic Viewpoint. CoRR (2023)
Jaeyoung Cha, Jaewook Lee, Chulhee Yun
Tighter Lower Bounds for Shuffling SGD: Random Permutations and Beyond. CoRR (2023)
David Xing Wu, Chulhee Yun, Suvrit Sra
On the Training Instability of Shuffling SGD with Batch Normalization. ICML (2023)
Dongkuk Si, Chulhee Yun
Practical Sharpness-Aware Minimization Cannot Converge All the Way to Optima. NeurIPS (2023)
David X. Wu, Chulhee Yun, Suvrit Sra
On the Training Instability of Shuffling SGD with Batch Normalization. CoRR (2023)
Hojoon Lee, Hanseul Cho, Hyunseung Kim, Daehoon Gwak, Joonkee Kim, Jaegul Choo, Se-Young Yun, Chulhee Yun
PLASTIC: Improving Input and Label Plasticity for Sample Efficient Reinforcement Learning. NeurIPS (2023)
Minhak Song, Chulhee Yun
Trajectory Alignment: Understanding the Edge of Stability Phenomenon via Bifurcation Theory. CoRR (2023)
Minhak Song, Chulhee Yun
Trajectory Alignment: Understanding the Edge of Stability Phenomenon via Bifurcation Theory. NeurIPS (2023)
Junsoo Oh, Chulhee Yun
Provable Benefit of Mixup for Finding Optimal Decision Boundaries. CoRR (2023)
Prin Phunyaphibarn, Junghyun Lee, Bohan Wang, Huishuai Zhang, Chulhee Yun
Large Catapults in Momentum Gradient Descent with Warmup: An Empirical Study. CoRR (2023)
Dongkuk Si, Chulhee Yun
Practical Sharpness-Aware Minimization Cannot Converge All the Way to Optima. CoRR (2023)
Jaeyoung Cha, Jaewook Lee, Chulhee Yun
Tighter Lower Bounds for Shuffling SGD: Random Permutations and Beyond. ICML (2023)
Junsoo Oh, Chulhee Yun
Provable Benefit of Mixup for Finding Optimal Decision Boundaries. ICML (2023)
Kwangjun Ahn, Xiang Cheng, Minhak Song, Chulhee Yun, Ali Jadbabaie, Suvrit Sra
Linear attention is (maybe) all you need (to understand transformer optimization). CoRR (2023)
Junghyun Lee, Hanseul Cho, Se-Young Yun, Chulhee Yun
Fair Streaming Principal Component Analysis: Statistical and Algorithmic Viewpoint. NeurIPS (2023)
Hanseul Cho, Chulhee Yun
SGDA with shuffling: faster convergence for nonconvex-PŁ minimax optimization. ICLR (2023)
Chulhee Yun, Shashank Rajput, Suvrit Sra
Minibatch vs Local SGD with Shuffling: Tight Convergence Bounds and Beyond. ICLR (2022)
Hanseul Cho, Chulhee Yun
SGDA with shuffling: faster convergence for nonconvex-PŁ minimax optimization. CoRR (2022)
Sejun Park, Chulhee Yun, Jaeho Lee, Jinwoo Shin
Minimum Width for Universal Approximation. ICLR (2021)
Chulhee Yun, Suvrit Sra, Ali Jadbabaie
Open Problem: Can Single-Shuffle SGD be Better than Reshuffling SGD and GD? COLT (2021)
Chulhee Yun, Shashank Rajput, Suvrit Sra
Minibatch vs Local SGD with Shuffling: Tight Convergence Bounds and Beyond. CoRR (2021)
Chulhee Yun, Shankar Krishnan, Hossein Mobahi
A unifying view on implicit bias in training linear neural networks. ICLR (2021)
Sejun Park, Jaeho Lee, Chulhee Yun, Jinwoo Shin
Provable Memorization via Deep Neural Networks using Sub-linear Parameters. COLT (2021)
Chulhee Yun, Suvrit Sra, Ali Jadbabaie
Can Single-Shuffle SGD be Better than Reshuffling SGD and GD? CoRR (2021)
Chulhee Yun, Shankar Krishnan, Hossein Mobahi
A Unifying View on Implicit Bias in Training Linear Neural Networks. CoRR (2020)
Srinadh Bhojanapalli, Chulhee Yun, Ankit Singh Rawat, Sashank J. Reddi, Sanjiv Kumar
Low-Rank Bottleneck in Multi-head Attention Models. CoRR (2020)
Chulhee Yun, Srinadh Bhojanapalli, Ankit Singh Rawat, Sashank J. Reddi, Sanjiv Kumar
Are Transformers universal approximators of sequence-to-sequence functions? ICLR (2020)
Sejun Park, Jaeho Lee, Chulhee Yun, Jinwoo Shin
Provable Memorization via Deep Neural Networks using Sub-linear Parameters. CoRR (2020)
Srinadh Bhojanapalli, Chulhee Yun, Ankit Singh Rawat, Sashank J. Reddi, Sanjiv Kumar
Low-Rank Bottleneck in Multi-head Attention Models. ICML (2020)
Chulhee Yun, Yin-Wen Chang, Srinadh Bhojanapalli, Ankit Singh Rawat, Sashank J. Reddi, Sanjiv Kumar
$O(n)$ Connections are Expressive Enough: Universal Approximability of Sparse Transformers. CoRR (2020)
Sejun Park, Chulhee Yun, Jaeho Lee, Jinwoo Shin
Minimum Width for Universal Approximation. CoRR (2020)
Chulhee Yun, Yin-Wen Chang, Srinadh Bhojanapalli, Ankit Singh Rawat, Sashank J. Reddi, Sanjiv Kumar
O(n) Connections are Expressive Enough: Universal Approximability of Sparse Transformers. NeurIPS (2020)
Kwangjun Ahn, Chulhee Yun, Suvrit Sra
SGD with shuffling: optimal rates without component convexity and large epoch requirements. NeurIPS (2020)
Chulhee Yun, Srinadh Bhojanapalli, Ankit Singh Rawat, Sashank J. Reddi, Sanjiv Kumar
Are Transformers universal approximators of sequence-to-sequence functions? CoRR (2019)
Chulhee Yun, Suvrit Sra, Ali Jadbabaie
Are deep ResNets provably better than linear predictors? NeurIPS (2019)
Chulhee Yun, Suvrit Sra, Ali Jadbabaie
Are deep ResNets provably better than linear predictors? CoRR (2019)
Chulhee Yun, Suvrit Sra, Ali Jadbabaie
Small nonlinearities in activation functions create bad local minima in neural networks. ICLR (Poster) (2019)
Chulhee Yun, Suvrit Sra, Ali Jadbabaie
Small ReLU networks are powerful memorizers: a tight analysis of memorization capacity. NeurIPS (2019)
Chulhee Yun, Suvrit Sra, Ali Jadbabaie
Efficiently testing local optimality and escaping saddles for ReLU networks. ICLR (Poster) (2019)
Chulhee Yun, Suvrit Sra, Ali Jadbabaie
Efficiently testing local optimality and escaping saddles for ReLU networks. CoRR (2018)
Chulhee Yun, Suvrit Sra, Ali Jadbabaie
A Critical View of Global Optimality in Deep Learning. CoRR (2018)
Chulhee Yun, Suvrit Sra, Ali Jadbabaie
Finite sample expressive power of small-width ReLU networks. CoRR (2018)
Chulhee Yun, Suvrit Sra, Ali Jadbabaie
Global Optimality Conditions for Deep Neural Networks. ICLR (Poster) (2018)
John C. Duchi, Feng Ruan, Chulhee Yun
Minimax Bounds on Stochastic Batched Convex Optimization. COLT (2018)
Chulhee Yun, Suvrit Sra, Ali Jadbabaie
Global optimality conditions for deep neural networks. CoRR (2017)
Chulhee Yun, Donghoon Lee, Chang Dong Yoo
Face detection using Local Hybrid Patterns. ICASSP (2015)
Chulhee Yun, Jaegon Ahn, Yeon-Ho Kim
A fusion of computer vision technique and a visual programming language for edutainment robots. ISR (2013)
Chulhee Yun, Jaegon Ahn, Yeon-Ho Kim
An implementation of computer vision technique for an edutainment robot with a visual programming language. URAI (2013)