Hit papers significantly outperform the citation benchmark for their cohort. A paper qualifies
if it has ≥500 total citations, achieves ≥1.5× the top-1% citation threshold for papers in the
same subfield and year (this is the minimum needed to enter the top 1%, not the average
within it), or reaches the top citation threshold in at least one of its specific research
topics.
Parallel Restarted SGD with Faster Convergence and Less Communication: Demystifying Why Model Averaging Works for Deep Learning
2019302 citationsHao Yu, Sen Yang et al.Proceedings of the AAAI Conference on Artificial Intelligenceprofile →
Peers — A (Enhanced Table)
Peers by citation overlap · career bar shows stage (early→late)
cites ·
hero ref
This map shows the geographic impact of Shenghuo Zhu's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by Shenghuo Zhu with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Shenghuo Zhu more than expected).
This network shows the impact of papers produced by Shenghuo Zhu. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by Shenghuo Zhu. The network helps show where Shenghuo Zhu may publish in the future.
Co-authorship network of co-authors of Shenghuo Zhu
This figure shows the co-authorship network connecting the top 25 collaborators of Shenghuo Zhu.
A scholar is included among the top collaborators of Shenghuo Zhu based on the total number of
citations received by their joint publications. Widths of edges
represent the number of papers authors have co-authored together.
Node borders
signify the number of papers an author published with Shenghuo Zhu. Shenghuo Zhu is excluded from
the visualization to improve readability, since they are connected to all nodes in the network.
All Works
20 of 20 papers shown
1.
Yu, Hao, Sen Yang, & Shenghuo Zhu. (2018). Parallel Restarted SGD for Non-Convex Optimization with Faster Convergence and Less Communication.. arXiv (Cornell University).17 indexed citations
2.
Xu, Yi, et al.. (2018). Learning with Non-Convex Truncated Losses by SGD. Uncertainty in Artificial Intelligence. 701–711.3 indexed citations
Qian, Qi, Rong Jin, Shenghuo Zhu, & Yuanqing Lin. (2014). An Integrated Framework for High Dimensional Distance Metric Learning and Its Application to Fine-Grained Visual Categorization.. arXiv (Cornell University).5 indexed citations
6.
Yang, Tianbao, Shenghuo Zhu, Rong Jin, & Yuanqing Lin. (2013). On Theoretical Analysis of Distributed Stochastic Dual Coordinate Ascent.. arXiv (Cornell University).2 indexed citations
7.
Zou, Will Y., Shenghuo Zhu, Kai Yu, & Andrew Y. Ng. (2012). Deep Learning of Invariant Features via Simulated Fixations in Video. Neural Information Processing Systems. 25. 3203–3211.87 indexed citations
8.
Yang, Tianbao, et al.. (2012). Online Optimization with Gradual Variations. Conference on Learning Theory. 23.40 indexed citations
9.
Mahdavi, Mehrdad, Tianbao Yang, Rong Jin, Shenghuo Zhu, & Jinfeng Yi. (2012). Stochastic Gradient Descent with Only One Projection. Neural Information Processing Systems. 25. 494–502.19 indexed citations
10.
Lin, Yuanqing, Tong Zhang, Shenghuo Zhu, & Kai Yu. (2010). Deep Coding Network. Rare & Special e-Zone (The Hong Kong University of Science and Technology). 23. 1405–1413.17 indexed citations
Lin, Yuanqing, Shenghuo Zhu, Daniel J. Lee, & Ben Taskar. (2009). Learning Sparse Markov Network Structure via Ensemble-of-Trees Models. International Conference on Artificial Intelligence and Statistics. 360–367.7 indexed citations
13.
Yang, Tianbao, Rong Jin, Yün Chi, & Shenghuo Zhu. (2009). A Bayesian framework for community detection integrating content and link. Uncertainty in Artificial Intelligence. 615–622.7 indexed citations
14.
Zhu, Shenghuo, Kai Yu, & Yihong Gong. (2008). Stochastic Relational Models for Large-scale Dyadic Data using MCMC. Neural Information Processing Systems. 21. 1993–2000.15 indexed citations
15.
Zhu, Shenghuo, Tao Li, Zhiyuan Chen, Dingding Wang, & Yihong Gong. (2008). Dynamic active probing of helpdesk databases. Proceedings of the VLDB Endowment. 1(1). 748–760.3 indexed citations
Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive
bibliographic database. While OpenAlex provides broad and valuable coverage of the global
research landscape, it—like all bibliographic datasets—has inherent limitations. These include
incomplete records, variations in author disambiguation, differences in journal indexing, and
delays in data updates. As a result, some metrics and network relationships displayed in
Rankless may not fully capture the entirety of a scholar's output or impact.