EDBT 2026 Demo / reviewers in the wild / expert
Shijian Tang
dblp:120/1647
· DBLP profile ↗
2ranked-venue papers
1as first author
0since 2021 · last 2017
—ORCID · none
Domains — the database's venue-derived domains; a paper can count in several
Artificial intelligence and machine learning · 1Computer networks · 1 · 1 first-author
Expertise — from the expertise taxonomy: the topics of the expert's papers under the CCF categories. A weight counts papers with recency: 1 for a paper about the topic, 0.3 when the topic is its context, halved every five years.
| Artificial intelligence
1 paper |
Efficient and distributed learning · 91% Deep learning architectures and training · 9% | |
| Computer networks
1 paper |
Physical-layer communications · 100% |
Topics — the 7 heaviest of 7, each with the papers that count most for it
| Topic | Weight | Papers | Last | Evidence papers |
|---|---|---|---|---|
Machine learning › Efficient and distributed learning
model compression |
0.3 | 1 | 2017 | DSD: Dense-Sparse-Dense Training for Deep Neural Networks · ICLR (Poster) 2017 |
Machine learning › Efficient and distributed learning › model compression
pruning |
0.3 | 1 | 2017 | DSD: Dense-Sparse-Dense Training for Deep Neural Networks · ICLR (Poster) 2017 |
Machine learning › Efficient and distributed learning › model compression
sparse training |
0.3 | 1 | 2017 | DSD: Dense-Sparse-Dense Training for Deep Neural Networks · ICLR (Poster) 2017 |
Physical-layer communications › optical wireless communication
underwater optical communication |
0.2 | 1 | 2014 | Impulse Response Modeling for Underwater Wireless Optical Communication Links · IEEE Trans. Commun. 2014 |
Machine learning › Deep learning architectures and training › training optimization
training schedule |
0.1 | 1 | 2017 | DSD: Dense-Sparse-Dense Training for Deep Neural Networks · ICLR (Poster) 2017 |
Physical-layer communications › interference
intersymbol interference |
0.1 | 1 | 2014 | Impulse Response Modeling for Underwater Wireless Optical Communication Links · IEEE Trans. Commun. 2014 |
Physical-layer communications › equalization › linear equalization
zero-forcing equalization |
0.1 | 1 | 2014 | Impulse Response Modeling for Underwater Wireless Optical Communication Links · IEEE Trans. Commun. 2014 |
Methods — techniques the papers use, named apart from their topics
regularization · 0.3pruning · 0.3dense-sparse-dense training · 0.3monte carlo simulation · 0.2closed-form modeling · 0.2
| Year | Publication | Venue | Position |
|---|---|---|---|
| 2017 | DSD: Dense-Sparse-Dense Training for Deep Neural Networks
Song Han 0003, Jeff Pool, Sharan Narang, Huizi Mao, Enhao Gong, Shijian Tang, Erich Elsen, Peter Vajda, Manohar Paluri, Bryan Catanzaro, William J. Dally |
ICLR (Poster) | 6 |
| 2014 | Impulse Response Modeling for Underwater Wireless Optical Communication LinksabstractIn underwater wireless optical communication (UWOC) links, multiple scattering may cause temporal spread of beam pulse characterized by the impulse response, which therefore results in inter-symbol interference (ISI) and degrades system error performance. The impulse response of UWOC links has been investigated both theoretically and experimentally by researchers but has not been derived in simple closed-form to the best of our knowledge. In this paper, we analyze the optical characteristics of seawater and present a closed-form expression of double Gamma functions to model the channel impulse response. The double Gamma functions model fits well with Monte Carlo simulation results in turbid seawater such as coastal and harbor water. The bit-error-rate (BER) and channel bandwidth are further evaluated based on this model for various link ranges. Numerical results suggest that the temporal pulse spread strongly degrades the BER performance for high data rate UWOC systems with on-off keying (OOK) modulation and limits the channel bandwidth in turbid underwater environments. The zero-forcing (ZF) equalization designed based on our channel model has been adopted to overcome ISI and improve the system performance. It is plausible and convenient to utilize this impulse response model for performance analysis and system design of UWOC systems. Shijian Tang, Yuhan Dong, Xuedan Zhang |
IEEE Trans. Commun. | 1 |