Profiles2020-2024
Kwangjun Ahn
MIT EECS/LIDS
12Papers
0Last author
20Unique co-authors
9First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers12
- Linear attention is (maybe) all you need (to understand Transformer optimization)Author 1 of 6ICLR 2024 · 92 citations
- Understanding Adam Optimizer via Online Learning of Updates: Adam is FTRL in DisguiseAuthor 1 of 4ICML 2024 · 25 citations
- How to Escape Sharp Minima with Random PerturbationsAuthor 1 of 3ICML 2024 · 17 citations
- Transformers learn to implement preconditioned gradient descent for in-context learningAuthor 1 of 4NeurIPS 2023 · 324 citations
- The Crucial Role of Normalization in Sharpness-Aware MinimizationAuthor 2 of 6NeurIPS 2023 · 36 citations
- Learning threshold neurons via edge of stabilityAuthor 1 of 6NeurIPS 2023 · 5 citations
- Understanding the unstable convergence of gradient descentAuthor 1 of 3ICML 2022 · 89 citations
- Mirror Descent Maximizes Generalized Margin and Can Be Implemented EfficientlyAuthor 2 of 4NeurIPS 2022 · 33 citations
- Reproducibility in Optimization: Theoretical Framework and LimitsAuthor 1 of 6NeurIPS 2022 · 32 citations
- Agnostic Learnability of Halfspaces via Logistic LossAuthor 2 of 5ICML 2022 · 3 citations
- Efficient constrained sampling via the mirror-Langevin algorithmAuthor 1 of 2NeurIPS 2021 · 77 citations
- SGD with shuffling: optimal rates without component convexity and large epoch requirementsAuthor 1 of 2NeurIPS 2020 · 83 citations
