default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDJunhong Lin 0002
Person information
- affiliation: Zhejiang University (ZJU), Center for Data Science, Hangzhou, China
- affiliation: Massachusetts Institute of Technology (MIT), Laboratory for Computational and Statistical Learning (LCSL), Cambridge, MA, USA
- affiliation: Istituto Italiano di Tecnologia, Genoa, Italy
- affiliation (2013-2015): City University of Hong Kong, Department of Mathematics, Hong Kong
- affiliation (PhD 2013): Zhejiang University, Hangzhou, China
Other persons with the same name
- Junhong Lin (aka: Jun-Hong Lin) — disambiguation page
- Junhong Lin 0001
![[0000-0003-3869-1380]](https://devdomain4test.ir/img/orcid-mark.12x12.png "0000-0003-3869-1380")
— Peking University, School of Electronic and Computer Engineering, Shenzhen, China (and 1 more) - Junhong Lin 0003 — Zhejiang University, Center for Data Science, Hangzhou, China (and 1 more)
- Junhong Lin 0004 — Massachusetts Institute of Technology, MIT CSAIL, Department of Elctronics Engineering and Computer Science, Cambridge, MA, USA
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
2020 – today
- 2026
[j15]Hang Xu, Song Li, Junhong Lin:
Nonconvex deterministic matrix completion by projected gradient descent methods. J. Complex. 96: 102056 (2026)- 2025
- [j14]Yusu Hong, Junhong Lin:
High probability bounds on AdaGrad for constrained weakly convex optimization. J. Complex. 86: 101889 (2025) - [c5]Yusu Hong, Junhong Lin:
Theoretical Investigation of Adafactor for Non-Convex Smooth Optimization. NeurIPS 2025 - 2024
- [j13]Hang Xu, Song Li, Junhong Lin:
Convergence of projected subgradient method with sparse or low-rank constraints. Adv. Comput. Math. 50(4): 62 (2024) - [c4]Yusu Hong, Junhong Lin:
On Convergence of Adam for Stochastic Optimization under Relaxed Assumptions. NeurIPS 2024 - [c3]Yusu Hong, Junhong Lin:
Revisiting Convergence of AdaGrad with Relaxed Assumptions. UAI 2024: 1727-1750 - [i11]Hang Xu, Song Li, Junhong Lin:
Nonconvex Deterministic Matrix Completion by Projected Gradient Descent Methods. CoRR abs/2401.06592 (2024) - [i10]Yusu Hong, Junhong Lin:
On Convergence of Adam for Stochastic Optimization under Relaxed Assumptions. CoRR abs/2402.03982 (2024) - [i9]Yusu Hong, Junhong Lin:
Revisiting Convergence of AdaGrad with Relaxed Assumptions. CoRR abs/2402.13794 (2024) - 2023
- [i8]Yusu Hong, Junhong Lin:
High Probability Convergence of Adam Under Unbounded Gradients and Affine Variance Noise. CoRR abs/2311.02000 (2023) - 2020
- [j12]Song Li, Junhong Lin, Dekai Liu, Wenchang Sun:
Iterative hard thresholding for compressed data separation. J. Complex. 59: 101469 (2020)
2010 – 2019
- 2018
- [j11]Junhong Lin, Lorenzo Rosasco, Silvia Villa, Ding-Xuan Zhou:
Modified Fejér sequences and applications. Comput. Optim. Appl. 71(1): 95-113 (2018) - [j10]Junhong Lin, Lorenzo Rosasco:
Generalization properties of doubly stochastic learning algorithms. J. Complex. 47: 42-61 (2018) - [j9]Junhong Lin, Ding-Xuan Zhou:
Online Learning Algorithms Can Converge Comparably Fast as Batch Learning. IEEE Trans. Neural Networks Learn. Syst. 29(6): 2367-2378 (2018) - 2017
- [j8]Junhong Lin, Yunwen Lei, Bo Zhang, Ding-Xuan Zhou:
Online pairwise learning algorithms with convex loss functions. Inf. Sci. 406: 57-70 (2017) - [j7]Junhong Lin, Lorenzo Rosasco:
Optimal Rates for Multi-pass Stochastic Gradient Methods. J. Mach. Learn. Res. 18: 97:1-97:47 (2017) - [i7]Junhong Lin, Lorenzo Rosasco:
Generalization Properties of Doubly Online Learning Algorithms. CoRR abs/1707.00577 (2017) - [i6]Junhong Lin, Lorenzo Rosasco:
Optimal Rates for Learning with Nyström Stochastic Gradient Methods. CoRR abs/1710.07797 (2017) - 2016
- [j6]Junhong Lin, Lorenzo Rosasco, Ding-Xuan Zhou:
Iterative Regularization for Learning with Convex Loss Functions. J. Mach. Learn. Res. 17: 77:1-77:38 (2016) - [j5]Junhong Lin, Song Li:
Restricted q-Isometry Properties Adapted to Frames for Nonconvex lq-Analysis. IEEE Trans. Inf. Theory 62(8): 4733-4747 (2016) - [c2]Junhong Lin, Raffaello Camoriano, Lorenzo Rosasco:
Generalization Properties and Implicit Regularization for Multiple Passes SGM. ICML 2016: 2340-2348 - [c1]Junhong Lin, Lorenzo Rosasco:
Optimal Learning for Multi-pass Stochastic Gradient Methods. NIPS 2016: 4556-4564 - [i5]Junhong Lin, Song Li:
Restricted $q$-Isometry Properties Adapted to Frames for Nonconvex $l_q$-Analysis. CoRR abs/1602.06399 (2016) - [i4]Junhong Lin, Raffaello Camoriano, Lorenzo Rosasco:
Generalization Properties and Implicit Regularization for Multiple Passes SGM. CoRR abs/1605.08375 (2016) - [i3]Junhong Lin, Lorenzo Rosasco:
Optimal Learning for Multi-pass Stochastic Gradient Methods. CoRR abs/1605.08882 (2016) - 2015
- [j4]Junhong Lin, Ding-Xuan Zhou:
Learning theory of randomized Kaczmarz algorithm. J. Mach. Learn. Res. 16: 3341-3365 (2015) - 2013
- [j3]Junhong Lin, Song Li:
Nonuniform support recovery from noisy random measurements by Orthogonal Matching Pursuit. J. Approx. Theory 165(1): 20-40 (2013) - [j2]Junhong Lin, Song Li, Yi Shen:
Compressed Data Separation With Redundant Dictionaries. IEEE Trans. Inf. Theory 59(7): 4309-4315 (2013) - [j1]Junhong Lin, Song Li, Yi Shen:
New Bounds for Restricted Isometry Constants With Coherent Tight Frames. IEEE Trans. Signal Process. 61(3): 611-621 (2013) - [i2]Junhong Lin, Song Li:
Sparse Recovery with Coherent Tight Frame via Analysis Dantzig Selector and Analysis LASSO. CoRR abs/1301.3248 (2013) - 2011
- [i1]Song Li, Junhong Lin:
Compressed Sensing with coherent tight frames via $l_q$-minimization for $0<q\leq1$. CoRR abs/1105.3299 (2011)
Coauthor Index
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 2026-06-29 01:21 CEST by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated, funded, and maintained by:
Schloss Dagstuhl - Leibniz Center for Informatics is a member of the Leibniz Association and is funded by the federal government of Germany and the states of Germany, especially Saarland and Rhineland‑Palatinate.
