Volgen
Chulhee Yun
Chulhee Yun
Assistant Professor, KAIST Kim Jaechul Graduate School of AI
Geverifieerd e-mailadres voor kaist.ac.kr - Homepage
Titel
Geciteerd door
Geciteerd door
Jaar
Are Transformers universal approximators of sequence-to-sequence functions?
C Yun, S Bhojanapalli, AS Rawat, SJ Reddi, S Kumar
ICLR 2020 (arXiv:1912.10077), 2019
1152019
Small nonlinearities in activation functions create bad local minima in neural networks
C Yun, S Sra, A Jadbabaie
ICLR 2019 (arXiv:1802.03487), 2018
113*2018
Global optimality conditions for deep neural networks
C Yun, S Sra, A Jadbabaie
ICLR 2018 (arXiv:1707.02444), 2017
1042017
Small ReLU networks are powerful memorizers: a tight analysis of memorization capacity
C Yun, S Sra, A Jadbabaie
NeurIPS 2019 (arXiv:1810.07770), 2019
772019
Minimum width for universal approximation
S Park, C Yun, J Lee, J Shin
ICLR 2021 (arXiv:2006.08859), 2020
672020
A Unifying View on Implicit Bias in Training Linear Neural Networks
C Yun, S Krishnan, H Mobahi
ICLR 2021 (arXiv:2010.02501), 2020
392020
Low-Rank Bottleneck in Multi-head Attention Models
S Bhojanapalli, C Yun, AS Rawat, SJ Reddi, S Kumar
ICML 2020 (arXiv:2002.07028), 2020
372020
SGD with shuffling: optimal rates without component convexity and large epoch requirements
K Ahn*, C Yun*, S Sra
NeurIPS 2020 (arXiv:2006.06946), 2020
312020
Connections are Expressive Enough: Universal Approximability of Sparse Transformers
C Yun, YW Chang, S Bhojanapalli, AS Rawat, SJ Reddi, S Kumar
NeurIPS 2020 (arXiv:2006.04862), 2020
292020
Minimax bounds on stochastic batched convex optimization
J Duchi, F Ruan, C Yun
Conference On Learning Theory, 3065-3162, 2018
252018
Minibatch vs local SGD with shuffling: Tight convergence bounds and beyond
C Yun, S Rajput, S Sra
ICLR 2022 (arXiv:2110.10342), 2021
132021
Provable Memorization via Deep Neural Networks using Sub-linear Parameters
S Park, J Lee, C Yun, J Shin
COLT 2021 (arXiv:2010.13363), 2020
132020
Are deep ResNets provably better than linear predictors?
C Yun, S Sra, A Jadbabaie
NeurIPS 2019 (arXiv:1907.03922), 2019
122019
Open Problem: Can Single-Shuffle SGD be Better than Reshuffling SGD and GD?
C Yun, S Sra, A Jadbabaie
COLT 2021 (arXiv:2103.07079), 2021
11*2021
Efficiently testing local optimality and escaping saddles for ReLU networks
C Yun, S Sra, A Jadbabaie
ICLR 2019 (arXiv:1809.10858), 2018
72018
SGDA with shuffling: faster convergence for nonconvex-PŁ minimax optimization
H Cho, C Yun
ICLR 2023 (arXiv:2210.05995), 2022
2022
Optimization for Deep Learning: Bridging the Theory-Practice Gap
C Yun
Massachusetts Institute of Technology, 2021
2021
Face detection using Local Hybrid Patterns
C Yun, D Lee, CD Yoo
2015 IEEE International Conference on Acoustics, Speech and Signal …, 2015
2015
Het systeem kan de bewerking nu niet uitvoeren. Probeer het later opnieuw.
Artikelen 1–18