[AI Seminar] AI Seminar sponsored by Apple -- Nika Haghtalab -- Nov 14
Adams Wei Yu
weiyu at cs.cmu.edu
Sat Nov 11 18:03:08 EST 2017
Dear faculty and students,
We look forward to seeing you next Tuesday, Nov 14, at noon in NSH 3305 for
AI Seminar sponsored by Apple. To learn more about the seminar series,
please visit the AI Seminar webpage <http://www.cs.cmu.edu/~aiseminar/>.
On Tuesday, Nika Haghtalab <https://www.cs.cmu.edu/~nhaghtal/> will give
the following talk:
Title: Algorithms for Generalized Topic Modeling
Topic modeling is an area with significant recent work in the intersection
of algorithms and machine learning. In standard topic models, a topic (such
as sports, business, or politics) is viewed as a probability distribution
\vec a_i over words, and a document is generated by first selecting a
mixture \vec w over topics, and then generating words iid from the
associated mixture \vec w^T A. Given a large collection of such documents,
the goal is to recover the topic vectors and then to correctly classify new
documents according to their topic mixture.
In this work we consider a broad generalization of this framework in which
words are no longer assumed to be drawn iid and instead a topic is a
complex distribution over sequences of paragraphs. Since one could not hope
to even represent such a distribution in general (even if paragraphs are
given using some natural feature representation), we aim instead to
directly learn a document classifier. That is, we aim to learn a predictor
that given a new document, accurately predicts its topic mixture, without
learning the distributions explicitly. We present several natural
conditions under which one can do this efficiently and discuss issues such
as noise tolerance and sample complexity in this model. More generally, our
model can be viewed as a generalization of the multi-view or co-training
setting in machine learning.
This talk is based on joint work with Avrim Blum. To appear in AAAI 2018.
-------------- next part --------------
An HTML attachment was scrubbed...
More information about the ai-seminar-announce