Joint Theory Lunch Seminar / Computer Science Speaking Skills Talk

— 1:00pm

Location:
In Person and Virtual - ET - Gates Hillman 8102 and Zoom

Speaker:
DRAVYANSH SHARMA , Ph.D. Student
Computer Science Department
Carnegie Mellon University

https://www.cs.cmu.edu/~dravyans/

Data-driven semi-supervised learning

We consider a novel data driven approach for designing learning algorithms that can effectively learn with only a small number of labeled examples. This is crucial for modern machine learning applications where labels are scarce or expensive to obtain. We focus on graph-based techniques, where the unlabeled examples are connected in a graph under the implicit assumption that similar nodes likely have similar labels. Over the past decades, several elegant graph-based semi-supervised learning algorithms for how to infer the labels of the unlabeled examples given the graph and a few labeled examples have been proposed. However, the problem of how to create the graph (which impacts the practical usefulness of these methods significantly) has been relegated to domain-specific art and heuristics and no general principles have been proposed. In this work we present a novel data driven approach for learning the graph and provide strong formal guarantees in both the distributional and online learning formalizations. We show how to leverage problem instances coming from an underlying problem domain to learn the graph hyperparameters from commonly used parametric families of graphs that perform well on new instances coming from the same domain. We also show how to combine several very different similarity metrics and learn multiple hyperparameters, providing general techniques to apply to large classes of problems. We expect some of the tools and techniques we develop along the way to be of interest beyond semi-supervised learning, for data driven algorithms for combinatorial problems more generally. This is based on joint work with Nina Balcan, and appears as an oral talk at NeurIPS 2021.

Presented in Partial Fulfillment of the CSD Speaking Skills Requirement. The Theory Lunch Seminar is sponsored in part by Smart Contract Research Forum In Person and Zoom Participation. See announcement.

For More Information:
deb@cs.cmu.edu


Add event to Google
Add event to iCal