Kwangjun Ahn

According to our database, Kwangjun Ahn authored at least 32 papers between 2017 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of three.

2024

Improved Sample Complexity of Imitation Learning for Barrier Model Predictive Control.

Daniel Pfrommer, Swati Padmanabhan, Kwangjun Ahn, Jack Umenberger, Tobia Marcucci, Zakaria Mhammedi, Ali Jadbabaie

CoRR, 2024

Adam with model exponential moving average is effective for nonconvex optimization.

Kwangjun Ahn, Ashok Cutkosky

CoRR, 2024

Does SGD really happen in tiny subspaces?

Minhak Song, Kwangjun Ahn, Chulhee Yun

CoRR, 2024

Understanding Adam Optimizer via Online Learning of Updates: Adam is FTRL in Disguise.

Kwangjun Ahn, Zhiyu Zhang, Yunbum Kook, Yan Dai

Proceedings of the Forty-first International Conference on Machine Learning, 2024

How to Escape Sharp Minima with Random Perturbations.

Kwangjun Ahn, Ali Jadbabaie, Suvrit Sra

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Linear attention is (maybe) all you need (to understand Transformer optimization).

Kwangjun Ahn, Xiang Cheng, Minhak Song, Chulhee Yun, Ali Jadbabaie, Suvrit Sra

Proceedings of the Twelfth International Conference on Learning Representations, 2024

2023

A Unified Approach to Controlling Implicit Regularization via Mirror Descent.

Haoyuan Sun, Khashayar Gatmiry, Kwangjun Ahn, Navid Azizan

J. Mach. Learn. Res., 2023

Smooth Model Predictive Control with Applications to Statistical Learning.

Kwangjun Ahn, Daniel Pfrommer, Jack Umenberger, Tobia Marcucci, Zakaria Mhammedi, Ali Jadbabaie

CoRR, 2023

How to escape sharp minima.

Kwangjun Ahn, Ali Jadbabaie, Suvrit Sra

CoRR, 2023

Transformers learn to implement preconditioned gradient descent for in-context learning.

Kwangjun Ahn, Xiang Cheng, Hadi Daneshmand, Suvrit Sra

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Learning threshold neurons via edge of stability.

Kwangjun Ahn, Sébastien Bubeck, Sinho Chewi, Yin Tat Lee, Felipe Suarez, Yi Zhang

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

The Crucial Role of Normalization in Sharpness-Aware Minimization.

Yan Dai, Kwangjun Ahn, Suvrit Sra

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Model Predictive Control via On-Policy Imitation Learning.

Kwangjun Ahn, Zakaria Mhammedi, Horia Mania, Zhang-Wei Hong, Ali Jadbabaie

Proceedings of the Learning for Dynamics and Control Conference, 2023

2022

Understanding Nesterov's Acceleration via Proximal Point Method.

Kwangjun Ahn, Suvrit Sra

Proceedings of the 5th Symposium on Simplicity in Algorithms, 2022

Mirror Descent Maximizes Generalized Margin and Can Be Implemented Efficiently.

Haoyuan Sun, Kwangjun Ahn, Christos Thrampoulidis, Navid Azizan

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Reproducibility in Optimization: Theoretical Framework and Limits.

Kwangjun Ahn, Prateek Jain, Ziwei Ji, Satyen Kale, Praneeth Netrapalli, Gil I. Shamir

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Agnostic Learnability of Halfspaces via Logistic Loss.

Ziwei Ji, Kwangjun Ahn, Pranjal Awasthi, Satyen Kale, Stefani Karp

Proceedings of the International Conference on Machine Learning, 2022

Understanding the unstable convergence of gradient descent.

Kwangjun Ahn, Jingzhao Zhang, Suvrit Sra

Proceedings of the International Conference on Machine Learning, 2022

One-Pass Learning via Bridging Orthogonal Gradient Descent and Recursive Least-Squares.

Youngjae Min, Kwangjun Ahn, Navid Azizan

Proceedings of the 61st IEEE Conference on Decision and Control, 2022

2021

Riemannian Perspective on Matrix Factorization.

Kwangjun Ahn, Felipe Suarez

CoRR, 2021

Efficient constrained sampling via the mirror-Langevin algorithm.

Kwangjun Ahn, Sinho Chewi

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Optimal dimension dependence of the Metropolis-Adjusted Langevin Algorithm.

Sinho Chewi, Chen Lu, Kwangjun Ahn, Xiang Cheng, Thibaut Le Gouic, Philippe Rigollet

Proceedings of the Conference on Learning Theory, 2021

2020

From Proximal Point Method to Nesterov's Acceleration.

Kwangjun Ahn

CoRR, 2020

On Tight Convergence Rates of Without-replacement SGD.

Kwangjun Ahn, Suvrit Sra

CoRR, 2020

SGD with shuffling: optimal rates without component convexity and large epoch requirements.

Kwangjun Ahn, Chulhee Yun, Suvrit Sra

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

From Nesterov's Estimate Sequence to Riemannian Acceleration.

Kwangjun Ahn, Suvrit Sra

Proceedings of the Conference on Learning Theory, 2020

A Simpler Strong Refutation of Random k-XOR.

Kwangjun Ahn

Proceedings of the Approximation, 2020

2019

Community Recovery in Hypergraphs.

Kwangjun Ahn, Kangwook Lee, Changho Suh

IEEE Trans. Inf. Theory, 2019

2018

Hypergraph Spectral Clustering in the Weighted Stochastic Block Model.

Kwangjun Ahn, Kangwook Lee, Changho Suh

IEEE J. Sel. Top. Signal Process., 2018

Binary Rating Estimation with Graph Side Information.

Kwangjun Ahn, Kangwook Lee, Hyunseung Cha, Changho Suh

Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

2017

Computing the maximum matching width is NP-hard.

Kwangjun Ahn, Jisu Jeong

CoRR, 2017

Information-theoretic limits of subspace clustering.

Kwangjun Ahn, Kangwook Lee, Changho Suh

Proceedings of the 2017 IEEE International Symposium on Information Theory, 2017