Junhong Lin

According to our database, Junhong Lin authored at least 25 papers between 2011 and 2025.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2025

High probability bounds on AdaGrad for constrained weakly convex optimization.

Yusu Hong, Junhong Lin

J. Complex., 2025

2024

Convergence of projected subgradient method with sparse or low-rank constraints.

Hang Xu, Song Li, Junhong Lin

Adv. Comput. Math., August, 2024

Nonconvex Deterministic Matrix Completion by Projected Gradient Descent Methods.

Hang Xu, Song Li, Junhong Lin

CoRR, 2024

Revisiting Convergence of AdaGrad with Relaxed Assumptions.

Yusu Hong, Junhong Lin

Proceedings of the Uncertainty in Artificial Intelligence, 2024

On Convergence of Adam for Stochastic Optimization under Relaxed Assumptions.

Yusu Hong, Junhong Lin

Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024

2023

High Probability Convergence of Adam Under Unbounded Gradients and Affine Variance Noise.

Yusu Hong, Junhong Lin

CoRR, 2023

2020

Iterative hard thresholding for compressed data separation.

Song Li, Junhong Lin, Dekai Liu, Wenchang Sun

J. Complex., 2020

2018

Online Learning Algorithms Can Converge Comparably Fast as Batch Learning.

Junhong Lin, Ding-Xuan Zhou

IEEE Trans. Neural Networks Learn. Syst., 2018

Generalization properties of doubly stochastic learning algorithms.

Junhong Lin, Lorenzo Rosasco

J. Complex., 2018

Modified Fejér sequences and applications.

Junhong Lin, Lorenzo Rosasco, Silvia Villa, Ding-Xuan Zhou

Comput. Optim. Appl., 2018

2017

Optimal Rates for Multi-pass Stochastic Gradient Methods.

Junhong Lin, Lorenzo Rosasco

J. Mach. Learn. Res., 2017

Online pairwise learning algorithms with convex loss functions.

Junhong Lin, Yunwen Lei, Bo Zhang, Ding-Xuan Zhou

Inf. Sci., 2017

Optimal Rates for Learning with Nyström Stochastic Gradient Methods.

Junhong Lin, Lorenzo Rosasco

CoRR, 2017

Generalization Properties of Doubly Online Learning Algorithms.

Junhong Lin, Lorenzo Rosasco

CoRR, 2017

2016

Restricted q-Isometry Properties Adapted to Frames for Nonconvex l_q-Analysis.

Junhong Lin, Song Li

IEEE Trans. Inf. Theory, 2016

Iterative Regularization for Learning with Convex Loss Functions.

Junhong Lin, Lorenzo Rosasco, Ding-Xuan Zhou

J. Mach. Learn. Res., 2016

Restricted $q$-Isometry Properties Adapted to Frames for Nonconvex $l_q$-Analysis.

Junhong Lin, Song Li

CoRR, 2016

Optimal Learning for Multi-pass Stochastic Gradient Methods.

Junhong Lin, Lorenzo Rosasco

Proceedings of the Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, 2016

Generalization Properties and Implicit Regularization for Multiple Passes SGM.

Junhong Lin, Raffaello Camoriano, Lorenzo Rosasco

Proceedings of the 33nd International Conference on Machine Learning, 2016

2015

Learning theory of randomized Kaczmarz algorithm.

Junhong Lin, Ding-Xuan Zhou

J. Mach. Learn. Res., 2015

2013

New Bounds for Restricted Isometry Constants With Coherent Tight Frames.

Junhong Lin, Song Li, Yi Shen

IEEE Trans. Signal Process., 2013

Compressed Data Separation With Redundant Dictionaries.

Junhong Lin, Song Li, Yi Shen

IEEE Trans. Inf. Theory, 2013

Nonuniform support recovery from noisy random measurements by Orthogonal Matching Pursuit.

Junhong Lin, Song Li

J. Approx. Theory, 2013

Sparse Recovery with Coherent Tight Frame via Analysis Dantzig Selector and Analysis LASSO

Junhong Lin, Song Li

CoRR, 2013

2011

Compressed Sensing with coherent tight frames via $l_q$-minimization for $0<q\leq1$

Song Li, Junhong Lin

CoRR, 2011