Upload

Loading icon Loading...

This video is unavailable.

Nina Balcan: Beyond Worst-Case Analysis in Machine Learning

Sign in to YouTube

Sign in with your Google Account (YouTube, Google+, Gmail, Orkut, Picasa, or Chrome) to like Stanford Computer Science Theo's video.

Sign in to YouTube

Sign in with your Google Account (YouTube, Google+, Gmail, Orkut, Picasa, or Chrome) to dislike Stanford Computer Science Theo's video.

Sign in to YouTube

Sign in with your Google Account (YouTube, Google+, Gmail, Orkut, Picasa, or Chrome) to add Stanford Computer Science Theo's video to your playlist.

Uploaded on Oct 16, 2011

Nina Balcan: Beyond Worst-Case Analysis in Machine Learning: Learning with Data Dependent Concept Spaces

In Machine Learning, there has been significant interest in using unlabeled data together with labeled data for learning (aka semi-supervised learning) due to the availability of large amounts of unlabeled data in many modern applications. This approach has been intensely explored in the machine learning community, with many heuristics and specific algorithms, as well as various successful experimental results being reported. However, the assumptions these methods are based on are often quite distinct and not captured by standard theoretical models. In this work we describe a PAC-style model designed with semi-supervised learning in mind, that can be used to help thinking about the problem of learning from labeled and unlabeled data and many of the different approaches taken. Our model provides a unified framework for analyzing when and why unlabeled data can help, and in which one can discuss both algorithmic and sample complexity issues. Conceptually, this work highlights the importance of using data-dependent concept spaces for learning.

Loading icon Loading...

Loading icon Loading...

Loading icon Loading...

Loading icon Loading...

Ratings have been disabled for this video.
Rating is available when the video has been rented.
This feature is not available right now. Please try again later.

Loading icon Loading...

Loading...
Working...
to add this to Watch Later

Add to