![](https://dblp.uni-trier.de./img/logo.ua.320x120.png)
![](https://dblp.uni-trier.de./img/dropdown.dark.16x16.png)
![](https://dblp.uni-trier.de./img/peace.dark.16x16.png)
Остановите войну!
for scientists:
![search dblp search dblp](https://dblp.uni-trier.de./img/search.dark.16x16.png)
![search dblp](https://dblp.uni-trier.de./img/search.dark.16x16.png)
default search action
Kwangjun Ahn
Person information
Refine list
![note](https://dblp.uni-trier.de./img/note-mark.dark.12x12.png)
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
2020 – today
- 2024
- [c19]Kwangjun Ahn, Xiang Cheng, Minhak Song, Chulhee Yun, Ali Jadbabaie, Suvrit Sra:
Linear attention is (maybe) all you need (to understand Transformer optimization). ICLR 2024 - [i25]Kwangjun Ahn, Zhiyu Zhang, Yunbum Kook, Yan Dai:
Understanding Adam Optimizer via Online Learning of Updates: Adam is FTRL in Disguise. CoRR abs/2402.01567 (2024) - [i24]Minhak Song, Kwangjun Ahn, Chulhee Yun:
Does SGD really happen in tiny subspaces? CoRR abs/2405.16002 (2024) - [i23]Kwangjun Ahn, Ashok Cutkosky:
Adam with model exponential moving average is effective for nonconvex optimization. CoRR abs/2405.18199 (2024) - 2023
- [c18]Kwangjun Ahn, Zakaria Mhammedi, Horia Mania, Zhang-Wei Hong, Ali Jadbabaie:
Model Predictive Control via On-Policy Imitation Learning. L4DC 2023: 1493-1505 - [c17]Yan Dai, Kwangjun Ahn, Suvrit Sra:
The Crucial Role of Normalization in Sharpness-Aware Minimization. NeurIPS 2023 - [c16]Kwangjun Ahn, Sébastien Bubeck, Sinho Chewi, Yin Tat Lee, Felipe Suarez, Yi Zhang:
Learning threshold neurons via edge of stability. NeurIPS 2023 - [c15]Kwangjun Ahn, Xiang Cheng, Hadi Daneshmand, Suvrit Sra:
Transformers learn to implement preconditioned gradient descent for in-context learning. NeurIPS 2023 - [i22]Yan Dai, Kwangjun Ahn, Suvrit Sra:
The Crucial Role of Normalization in Sharpness-Aware Minimization. CoRR abs/2305.15287 (2023) - [i21]Kwangjun Ahn, Ali Jadbabaie, Suvrit Sra:
How to escape sharp minima. CoRR abs/2305.15659 (2023) - [i20]Kwangjun Ahn, Xiang Cheng, Hadi Daneshmand, Suvrit Sra:
Transformers learn to implement preconditioned gradient descent for in-context learning. CoRR abs/2306.00297 (2023) - [i19]Kwangjun Ahn, Daniel Pfrommer, Jack Umenberger, Tobia Marcucci, Zakaria Mhammedi, Ali Jadbabaie:
Smooth Model Predictive Control with Applications to Statistical Learning. CoRR abs/2306.01914 (2023) - [i18]Haoyuan Sun, Khashayar Gatmiry, Kwangjun Ahn, Navid Azizan
:
A Unified Approach to Controlling Implicit Regularization via Mirror Descent. CoRR abs/2306.13853 (2023) - [i17]Kwangjun Ahn, Xiang Cheng, Minhak Song, Chulhee Yun, Ali Jadbabaie, Suvrit Sra:
Linear attention is (maybe) all you need (to understand transformer optimization). CoRR abs/2310.01082 (2023) - 2022
- [c14]Youngjae Min, Kwangjun Ahn, Navid Azizan
:
One-Pass Learning via Bridging Orthogonal Gradient Descent and Recursive Least-Squares. CDC 2022: 4720-4725 - [c13]Kwangjun Ahn, Jingzhao Zhang, Suvrit Sra:
Understanding the unstable convergence of gradient descent. ICML 2022: 247-257 - [c12]Ziwei Ji, Kwangjun Ahn, Pranjal Awasthi, Satyen Kale, Stefani Karp:
Agnostic Learnability of Halfspaces via Logistic Loss. ICML 2022: 10068-10103 - [c11]Kwangjun Ahn, Prateek Jain, Ziwei Ji, Satyen Kale, Praneeth Netrapalli, Gil I. Shamir:
Reproducibility in Optimization: Theoretical Framework and Limits. NeurIPS 2022 - [c10]Haoyuan Sun, Kwangjun Ahn, Christos Thrampoulidis, Navid Azizan:
Mirror Descent Maximizes Generalized Margin and Can Be Implemented Efficiently. NeurIPS 2022 - [c9]Kwangjun Ahn, Suvrit Sra:
Understanding Nesterov's Acceleration via Proximal Point Method. SOSA 2022: 117-130 - [i16]Ziwei Ji, Kwangjun Ahn, Pranjal Awasthi, Satyen Kale, Stefani Karp:
Agnostic Learnability of Halfspaces via Logistic Loss. CoRR abs/2201.13419 (2022) - [i15]Kwangjun Ahn, Prateek Jain, Ziwei Ji, Satyen Kale, Praneeth Netrapalli, Gil I. Shamir:
Reproducibility in Optimization: Theoretical Framework and Limits. CoRR abs/2202.04598 (2022) - [i14]Kwangjun Ahn, Jingzhao Zhang, Suvrit Sra:
Understanding the unstable convergence of gradient descent. CoRR abs/2204.01050 (2022) - [i13]Haoyuan Sun, Kwangjun Ahn, Christos Thrampoulidis, Navid Azizan
:
Mirror Descent Maximizes Generalized Margin and Can Be Implemented Efficiently. CoRR abs/2205.12808 (2022) - [i12]Youngjae Min, Kwangjun Ahn, Navid Azizan
:
One-Pass Learning via Bridging Orthogonal Gradient Descent and Recursive Least-Squares. CoRR abs/2207.13853 (2022) - [i11]Kwangjun Ahn, Zakaria Mhammedi, Horia Mania, Zhang-Wei Hong, Ali Jadbabaie:
Model Predictive Control via On-Policy Imitation Learning. CoRR abs/2210.09206 (2022) - [i10]Kwangjun Ahn, Sébastien Bubeck, Sinho Chewi, Yin Tat Lee, Felipe Suarez, Yi Zhang:
Learning threshold neurons via the "edge of stability". CoRR abs/2212.07469 (2022) - 2021
- [c8]Sinho Chewi, Chen Lu, Kwangjun Ahn, Xiang Cheng, Thibaut Le Gouic, Philippe Rigollet:
Optimal dimension dependence of the Metropolis-Adjusted Langevin Algorithm. COLT 2021: 1260-1300 - [c7]Kwangjun Ahn, Sinho Chewi:
Efficient constrained sampling via the mirror-Langevin algorithm. NeurIPS 2021: 28405-28418 - [i9]Kwangjun Ahn, Felipe Suarez:
Riemannian Perspective on Matrix Factorization. CoRR abs/2102.00937 (2021) - 2020
- [c6]Kwangjun Ahn
:
A Simpler Strong Refutation of Random k-XOR. APPROX-RANDOM 2020: 2:1-2:15 - [c5]Kwangjun Ahn, Suvrit Sra:
From Nesterov's Estimate Sequence to Riemannian Acceleration. COLT 2020: 84-118 - [c4]Kwangjun Ahn, Chulhee Yun, Suvrit Sra:
SGD with shuffling: optimal rates without component convexity and large epoch requirements. NeurIPS 2020 - [i8]Kwangjun Ahn, Suvrit Sra:
On Tight Convergence Rates of Without-replacement SGD. CoRR abs/2004.08657 (2020) - [i7]Kwangjun Ahn:
From Proximal Point Method to Nesterov's Acceleration. CoRR abs/2005.08304 (2020) - [i6]Kwangjun Ahn:
A simpler strong refutation of random k-XOR. CoRR abs/2008.03556 (2020) - [i5]Kwangjun Ahn, Sinho Chewi:
Efficient constrained sampling via the mirror-Langevin algorithm. CoRR abs/2010.16212 (2020) - [i4]Sinho Chewi, Chen Lu, Kwangjun Ahn, Xiang Cheng, Thibaut Le Gouic, Philippe Rigollet:
Optimal dimension dependence of the Metropolis-Adjusted Langevin Algorithm. CoRR abs/2012.12810 (2020)
2010 – 2019
- 2019
- [j2]Kwangjun Ahn
, Kangwook Lee
, Changho Suh
:
Community Recovery in Hypergraphs. IEEE Trans. Inf. Theory 65(10): 6561-6579 (2019) - 2018
- [j1]Kwangjun Ahn
, Kangwook Lee
, Changho Suh
:
Hypergraph Spectral Clustering in the Weighted Stochastic Block Model. IEEE J. Sel. Top. Signal Process. 12(5): 959-974 (2018) - [c3]Kwangjun Ahn, Kangwook Lee, Hyunseung Cha, Changho Suh:
Binary Rating Estimation with Graph Side Information. NeurIPS 2018: 4277-4288 - [i3]Kwangjun Ahn, Kangwook Lee, Changho Suh:
Hypergraph Spectral Clustering in the Weighted Stochastic Block Model. CoRR abs/1805.08956 (2018) - 2017
- [c2]Kwangjun Ahn, Kangwook Lee, Changho Suh
:
Information-theoretic limits of subspace clustering. ISIT 2017: 2473-2477 - [i2]Kwangjun Ahn, Kangwook Lee, Changho Suh:
Community Recovery in Hypergraphs. CoRR abs/1709.03670 (2017) - [i1]Kwangjun Ahn, Jisu Jeong:
Computing the maximum matching width is NP-hard. CoRR abs/1710.05117 (2017) - 2016
- [c1]Kwangjun Ahn, Kangwook Lee, Changho Suh
:
Community recovery in hypergraphs. Allerton 2016: 657-663
Coauthor Index
![](https://dblp.uni-trier.de./img/cog.dark.24x24.png)
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
Unpaywalled article links
Add open access links from to the list of external document links (if available).
Privacy notice: By enabling the option above, your browser will contact the API of unpaywall.org to load hyperlinks to open access articles. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Unpaywall privacy policy.
Archived links via Wayback Machine
For web page which are no longer available, try to retrieve content from the of the Internet Archive (if available).
Privacy notice: By enabling the option above, your browser will contact the API of archive.org to check for archived content of web pages that are no longer available. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Internet Archive privacy policy.
Reference lists
Add a list of references from ,
, and
to record detail pages.
load references from crossref.org and opencitations.net
Privacy notice: By enabling the option above, your browser will contact the APIs of crossref.org, opencitations.net, and semanticscholar.org to load article reference information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Crossref privacy policy and the OpenCitations privacy policy, as well as the AI2 Privacy Policy covering Semantic Scholar.
Citation data
Add a list of citing articles from and
to record detail pages.
load citations from opencitations.net
Privacy notice: By enabling the option above, your browser will contact the API of opencitations.net and semanticscholar.org to load citation information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the OpenCitations privacy policy as well as the AI2 Privacy Policy covering Semantic Scholar.
OpenAlex data
Load additional information about publications from .
Privacy notice: By enabling the option above, your browser will contact the API of openalex.org to load additional information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the information given by OpenAlex.
last updated on 2024-08-08 20:14 CEST by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint