| 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 | 363 | 2019 |
| Minimum width for universal approximation S Park, C Yun, J Lee, J Shin ICLR 2021 (arXiv:2006.08859), 2020 | 154 | 2020 |
| Small nonlinearities in activation functions create bad local minima in neural networks C Yun, S Sra, A Jadbabaie ICLR 2019 (arXiv:1802.03487), 2018 | 134* | 2018 |
| Small ReLU networks are powerful memorizers: a tight analysis of memorization capacity C Yun, S Sra, A Jadbabaie NeurIPS 2019 (arXiv:1810.07770), 2019 | 129 | 2019 |
| Global optimality conditions for deep neural networks C Yun, S Sra, A Jadbabaie ICLR 2018 (arXiv:1707.02444), 2017 | 118 | 2017 |
| A Unifying View on Implicit Bias in Training Linear Neural Networks C Yun, S Krishnan, H Mobahi ICLR 2021 (arXiv:2010.02501), 2020 | 91 | 2020 |
| Low-Rank Bottleneck in Multi-head Attention Models S Bhojanapalli, C Yun, AS Rawat, SJ Reddi, S Kumar ICML 2020 (arXiv:2002.07028), 2020 | 87 | 2020 |
| 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 | 74 | 2020 |
| SGD with shuffling: optimal rates without component convexity and large epoch requirements K Ahn*, C Yun*, S Sra NeurIPS 2020 (arXiv:2006.06946), 2020 | 73 | 2020 |
| Minibatch vs local SGD with shuffling: Tight convergence bounds and beyond C Yun, S Rajput, S Sra ICLR 2022 (arXiv:2110.10342), 2021 | 42 | 2021 |
| Provable memorization via deep neural networks using sub-linear parameters S Park, J Lee, C Yun, J Shin COLT 2021 (arXiv:2010.13363), 2021 | 36 | 2021 |
| Linear attention is (maybe) all you need (to understand transformer optimization) K Ahn, X Cheng, M Song, C Yun, A Jadbabaie, S Sra ICLR 2024 (arXiv:2310.01082), 2023 | 33 | 2023 |
| Minimax bounds on stochastic batched convex optimization J Duchi, F Ruan, C Yun Conference On Learning Theory, 3065-3162, 2018 | 29 | 2018 |
| PLASTIC: Improving Input and Label Plasticity for Sample Efficient Reinforcement Learning H Lee, H Cho, H Kim, D Gwak, J Kim, J Choo, SY Yun, C Yun NeurIPS 2023 (arXiv:2306.10711), 2023 | 24* | 2023 |
| 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 | 18* | 2021 |
| Tighter Lower Bounds for Shuffling SGD: Random Permutations and Beyond J Cha, J Lee, C Yun ICML 2023 (arXiv:2303.07160), 2023 | 17 | 2023 |
| Are deep ResNets provably better than linear predictors? C Yun, S Sra, A Jadbabaie NeurIPS 2019 (arXiv:1907.03922), 2019 | 16 | 2019 |
| Practical Sharpness-Aware Minimization Cannot Converge All the Way to Optima D Si, C Yun NeurIPS 2023 (arXiv:2306.09850), 2023 | 14 | 2023 |
| Efficiently testing local optimality and escaping saddles for ReLU networks C Yun, S Sra, A Jadbabaie ICLR 2019 (arXiv:1809.10858), 2018 | 11 | 2018 |
| Provable Benefit of Mixup for Finding Optimal Decision Boundaries J Oh, C Yun ICML 2023 (arXiv:2306.00267), 2023 | 8 | 2023 |
Suvrit SraTUM and MITVerified email at mit.edu
