Winter 2018




Jan 15
No Seminar (MLK Day)


Jan 22
Bren Hall 4011
1 pm
Shufeng Kong
PhD Candidate
Centre for Quantum Software and Information, FEIT
University of Technology Sydney, Australia

The Simple Temporal Problem (STP) is a fundamental temporal
reasoning problem and has recently been extended to
the Multiagent Simple Temporal Problem (MaSTP). In this
paper we present a novel approach that is based on enforcing
arc-consistency (AC) on the input (multiagent) simple temporal
network. We show that the AC-based approach is sufficient
for solving both the STP and MaSTP and provide efficient
algorithms for them. As our AC-based approach does
not impose new constraints between agents, it does not violate
the privacy of the agents and is superior to the state-ofthe-art
approach to MaSTP. Empirical evaluations on diverse
benchmark datasets also show that our AC-based algorithms
for STP and MaSTP are significantly more efficient than existing
Jan 29
Bren Hall 4011
1 pm
Postdoctoral Scholar
Paul Allen School of Computer Science and Engineering
University of Washington

Deep learning is one of the most important techniques used in natural language processing (NLP). A central question in deep learning for NLP is how to design a neural network that can fully utilize the information from training data and make accurate predictions. A key to solving this problem is to design a better network architecture.

In this talk, I will present two examples from my work on how structural information from natural language helps design better neural network models. The first example shows adding coreference structures of entities not only helps different aspects of text modeling, but also improves the performance of language generation; the second example demonstrates structures of organizing sentences into coherent texts can help neural networks build better representations for various text classification tasks. Along the lines of this topic, I will also propose a few ideas for future work and discuss some potential challenges.

February 5
No Seminar (AAAI)


February 12
Bren Hall 4011
1 pm
PhD Candidate
Computer Science
University of California, Irvine

Bayesian inference for complex models—the kinds needed to solve complex tasks such as object recognition—is inherently intractable, requiring analytically difficult integrals be solved in high dimensions. One solution is to turn to variational Bayesian inference: a parametrized family of distributions is proposed, and optimization is carried out to find the member of the family nearest to the true posterior. There is an innate trade-off within VI between expressive vs tractable approximations. We wish the variational family to be as rich as possible so as it might include the true posterior (or something very close), but adding structure to the approximation increases the computational complexity of optimization. As a result, there has been much interest in efficient optimization strategies for mixture model approximations. In this talk, I’ll return to the problem of using mixture models for VI. First, to motivate our approach, I’ll discuss the distinction between averaging vs combining variational models. We show that optimization objectives aimed at fitting mixtures (i.e. model combination), in practice, are relaxed into performing something between model combination and averaging. Our primary contribution is to formulate a novel training algorithm for variational model averaging by adapting Stein variational gradient descent to operate on the parameters of the approximating distribution. Then, through a particular choice of kernel, we show the algorithm can be adapted to perform something closer to model combination, providing a new algorithm for optimizing (finite) mixture approximations.
February 19
No Seminar (President’s Day)


February 26
Bren Hall 4011
1 pm
Research Scientist

Knowledge is an essential ingredient in the quest for artificial intelligence, yet scalable and robust approaches to acquiring knowledge have challenged AI researchers for decades. Often, the obstacle to knowledge acquisition is massive, uncertain, and changing data that obscures the underlying knowledge. In such settings, probabilistic models have excelled at exploiting the structure in the domain to overcome ambiguity, revise beliefs and produce interpretable results. In my talk, I will describe recent work using probabilistic models for knowledge graph construction and information extraction, including linking subjects across electronic health records, fusing background knowledge from scientific articles with gene association studies, disambiguating user browsing behavior across platforms and devices, and aligning structured data sources with textual summaries. I also highlight several areas of ongoing research, fusing embedding approaches with probabilistic modeling and building models that support dynamic data or human-in-the-loop interactions.

Jay Pujara is a research scientist at the University of Southern California’s Information Sciences Institute whose principal areas of research are machine learning, artificial intelligence, and data science. He completed a postdoc at UC Santa Cruz, earned his PhD at the University of Maryland, College Park and received his MS and BS at Carnegie Mellon University. Prior to his PhD, Jay spent six years at Yahoo! working on mail spam detection, user trust, and contextual mail experiences, and he has also worked at Google, LinkedIn and Oracle. Jay is the author of over thirty peer-reviewed publications and has received three best paper awards for his work. He is a recognized authority on knowledge graphs, and has organized the Automatic Knowledge Base Construction (AKBC) and Statistical Relational AI (StaRAI) workshops, has presented tutorials on knowledge graph construction at AAAI and WSDM, and has had his work featured in AI Magazine.

March 5
Bren Hall 4011
1 pm
Assistant Professor
UC Riverside

March 12
Bren Hall 4011
1 pm
PhD Student
UC Los Angeles

March 19
No Seminar (Finals Week)