F
Feng Niu
Researcher at University of Wisconsin-Madison
Publications - 22
Citations - 4693
Feng Niu is an academic researcher from University of Wisconsin-Madison. The author has contributed to research in topics: Markov chain & Inference. The author has an hindex of 15, co-authored 22 publications receiving 4491 citations. Previous affiliations of Feng Niu include Google.
Papers
More filters
Proceedings Article
Hogwild: A Lock-Free Approach to Parallelizing Stochastic Gradient Descent
TL;DR: In this paper, the authors present an update scheme called HOGWILD!, which allows processors access to shared memory with the possibility of overwriting each other's work, which achieves a nearly optimal rate of convergence.
Posted Content
HOGWILD!: A Lock-Free Approach to Parallelizing Stochastic Gradient Descent
TL;DR: This work aims to show using novel theoretical analysis, algorithms, and implementation that SGD can be implemented without any locking, and presents an update scheme called HOGWILD! which allows processors access to shared memory with the possibility of overwriting each other's work.
Journal ArticleDOI
Tuffy: scaling up statistical inference in Markov logic networks using an RDBMS
TL;DR: This work presents Tuffy, a scalable Markov Logic Networks framework that achieves scalability via three novel contributions: a bottom-up approach to grounding, a novel hybrid architecture that allows to perform AI-style local search efficiently using an RDBMS, and a theoretical insight that shows when one can improve the efficiency of stochastic local search.
Posted Content
Tuffy: Scaling up Statistical Inference in Markov Logic Networks using an RDBMS
TL;DR: Tuffy as mentioned in this paper proposes a bottom-up approach to grounding that allows to leverage the full power of the relational optimizer and performs AI-style local search efficiently using an RDBMS.
DeepDive: Web-scale Knowledge-base Construction using Statistical Learning and Inference
TL;DR: An end-to-end (live) demonstration system called DeepDive is presented that performs knowledge-base construction (KBC) from hundreds of millions of web pages and addresses the scalability challenges to achieve web-scale KBC.