Publications

Preprints:

  1. Riemannian Perspective on Matrix Factorization
    https://arxiv.org/abs/2102.00937
    Kwangjun Ahn and Felipe Suarez
    Feb. 2021
  2. Efficient constrained sampling via the mirror-Langevin algorithm
    https://arxiv.org/abs/2010.16212
    Kwangjun Ahn and Sinho Chewi
    Nov. 2020.
  3. From Proximal Point Method to Nesterov's Acceleration
    https://arxiv.org/pdf/2005.08304
    Kwangjun Ahn 
    May. 2020.
  4. Graph Matrices: Norm Bounds and Applications
    https://arxiv.org/abs/1604.03423
    Kwangjun Ahn, Dhruv Medarametla, and Aaron Potechin 
    Oct. 2020.

Published Works:

  1. Optimal dimension dependence of the Metropolis-Adjusted Langevin Algorithm
    http://proceedings.mlr.press/v134/chewi21a/chewi21a.pdf
    Sinho Chewi, Chen Lu, Kwangjun Ahn, Xiang Cheng, Thibaut Le Gouic, Philippe Rigollet
    34th Annual Conference on Learning Theory (COLT), Boulder, Colorado, Aug. 2021
  2. SGD with shuffling: optimal rates without component convexity and large epoch requirements
    https://proceedings.neurips.cc/paper/2020/hash/cb8acb1dc9821bf74e6ca9068032d623-Abstract.html
    Kwangjun Ahn, Chulhee Yun, and Suvrit Sra 
    Advances in Neural Information Processing Systems (NeurIPS), Dec. 2020.
    (Selected for Spotlight Presentation)
  3. A Simpler Strong Refutation of Random  k-XOR
    https://arxiv.org/abs/2008.03556
    Kwangjun Ahn
    International Conference on Randomization and Computation (RANDOM)  2020, Seattle, Washington, USA, Aug. 2020.
    https://youtu.be/cMVk3GU3XOg [talk video]
  4. From Nesterov's Estimate Sequence to Riemannian Acceleration
    http://proceedings.mlr.press/v125/ahn20a.html
    Kwangjun Ahn and Suvrit Sra
    Conference on Learning Theory (COLT), Graz, Austria, Jul. 2020. 
    https://youtu.be/e0rKq7NEwQk [talk video]
  5. Community Recovery in Hypergraphs
    https://ieeexplore.ieee.org/document/8730357
    Kwangjun Ahn, Kangwook Lee, and Changho Suh
    IEEE Transactions on Information Theory, vol. 65, no. 10, pp. 6561-6579, Oct. 2019.
  6. Binary Rating Estimation with Graph Side Information
    https://papers.nips.cc/paper/7681-binary-rating-estimation-with-graph-side-information  
    Kwangjun Ahn, Kangwook Lee, Hyunseung Cha, and Changho Suh
    Advances in Neural Information Processing Systems (NeurIPS),   Montreal, Canada, Dec. 2018. 
  7. Hypergraph Spectral Clustering in the Weighted Stochastic Block Model
    https://ieeexplore.ieee.org/document/8360467
    Kwangjun Ahn, Kangwook Lee, and Changho Suh
    IEEE Journal of Selected Topics in Signal Processing, vol. 12, no. 10, Oct. 2018. 
  8. Information-theoretic Limits of Subspace Clustering
    https://ieeexplore.ieee.org/document/8006974 
    Kwangjun Ahn, Kangwook Lee, and Changho Suh
    IEEE International Symposium on Information Theory (ISIT), Aachen, Germany, Jun. 2017.
  9. Community Recovery in Hypergraphs
    https://ieeexplore.ieee.org/document/7852294
    Kwangjun Ahn, Kangwook Lee, and Changho Suh
    The 53rd  Allerton Conference on Communication, Control, and Computing, Monticello, IL, USA, Sep. 2016. 

Technical Reports:

  1. Computing the Maximum Matching Width is NP-hard
    https://arxiv.org/abs/1710.05117
    Kwangjun Ahn and Jisu Jeong
    Sep. 2017.