Timezone: »
In this work we consider a setting where we have a very large number of related tasks with few examples from each individual task. Rather than either learning each task individually (and having a large generalization error) or learning all the tasks together using a single hypothesis (and suffering a potentially large inherent error), we consider learning a small pool of {\em shared hypotheses}. Each task is then mapped to a single hypothesis in the pool (hard association). We derive VC dimension generalization bounds for our model, based on the number of tasks, shared hypothesis and the VC dimension of the hypotheses class. We conducted experiments with both synthetic problems and sentiment of reviews, which strongly support our approach.
Author Information
Yacov Crammer (Technion)
Yishay Mansour (Tel-Aviv University)
More from the Same Authors
-
2022 Poster: Finite Sample Analysis Of Dynamic Regression Parameter Learning »
Mark Kozdoba · Edward Moroshko · Shie Mannor · Yacov Crammer -
2018 Poster: Efficient Loss-Based Decoding on Graphs for Extreme Classification »
Itay Evron · Edward Moroshko · Yacov Crammer -
2017 Poster: Rotting Bandits »
Nir Levine · Yacov Crammer · Shie Mannor -
2015 Poster: Linear Multi-Resource Allocation with Semi-Bandit Feedback »
Tor Lattimore · Yacov Crammer · Csaba Szepesvari -
2014 Poster: Learning Multiple Tasks in Parallel with a Shared Annotator »
Haim Cohen · Yacov Crammer -
2013 Workshop: Resource-Efficient Machine Learning »
Yevgeny Seldin · Yasin Abbasi Yadkori · Yacov Crammer · Ralf Herbrich · Peter Bartlett -
2012 Workshop: Multi-Trade-offs in Machine Learning »
Yevgeny Seldin · Guy Lever · John Shawe-Taylor · Nicolò Cesa-Bianchi · Yacov Crammer · Francois Laviolette · Gabor Lugosi · Peter Bartlett -
2012 Poster: Volume Regularization for Binary Classification »
Yacov Crammer · Tal Wagner -
2012 Spotlight: Volume Regularization for Binary Classification »
Yacov Crammer · Tal Wagner -
2011 Workshop: New Frontiers in Model Order Selection »
Yevgeny Seldin · Yacov Crammer · Nicolò Cesa-Bianchi · Francois Laviolette · John Shawe-Taylor -
2010 Poster: Learning via Gaussian Herding »
Yacov Crammer · Daniel Lee -
2010 Poster: New Adaptive Algorithms for Online Classification »
Francesco Orabona · Yacov Crammer -
2010 Poster: Learning Bounds for Importance Weighting »
Corinna Cortes · Yishay Mansour · Mehryar Mohri -
2009 Workshop: Advances in Ranking »
Shivani Agarwal · Chris J Burges · Yacov Crammer -
2009 Poster: Adaptive Regularization of Weight Vectors »
Yacov Crammer · Alex Kulesza · Mark Dredze -
2009 Spotlight: Adaptive Regularization of Weight Vectors »
Yacov Crammer · Alex Kulesza · Mark Dredze -
2008 Poster: Domain Adaptation with Multiple Sources »
Yishay Mansour · Mehryar Mohri · Afshin Rostamizadeh -
2008 Spotlight: Domain Adaptation with Multiple Sources »
Yishay Mansour · Mehryar Mohri · Afshin Rostamizadeh -
2008 Session: Oral session 6: Neural Coding »
Yacov Crammer -
2008 Poster: Exact Convex Confidence-Weighted Learning »
Yacov Crammer · Mark Dredze · Fernando Pereira -
2008 Spotlight: Exact Convex Confidence-Weighted Learning »
Yacov Crammer · Mark Dredze · Fernando Pereira -
2007 Poster: Learning Bounds for Domain Adaptation »
John Blitzer · Yacov Crammer · Alex Kulesza · Fernando Pereira · Jennifer Wortman Vaughan -
2006 Poster: Learning from Multiple Sources »
Yacov Crammer · Michael Kearns · Jennifer Wortman Vaughan -
2006 Poster: Analysis of Representations for Domain Adaptation »
John Blitzer · Shai Ben-David · Yacov Crammer · Fernando Pereira