Ohad Shamir - אוהד שמיר

I am a computer science Ph.D. student at the Machine Learning Lab in the Hebrew University.
My advisor is Prof. Naftali Tishby.

Publications

Journal Papers

• Stability and Model Selection in k-means Clustering
  Ohad Shamir and Naftali Tishby
  Accepted to Machine Learning Journal (COLT 2008 Special Issue).

• Learning to Classify with Missing and Corrupted Features
  Ofer Dekel and Ohad Shamir.
  To appear in Machine Learning Journal.

• Learning and Generalization with the Information Bottleneck
  Ohad Shamir, Sivan Sabato and Naftali Tishbi.
  To appear in Theoretical Computer Science (ALT 2008 Special Issue).

Conference Papers

• Vox Populi: Collecting High-Quality Labels from a Crowd
  Ofer Dekel and Ohad Shamir.
  22nd Annual Conference on Learning Theory (COLT 2009).
  

• Learnability and Stability in the General Learning Setting
  Shai Shalev-Shwartz, Ohad Shamir, Nathan Srebro and Karthik Sridharan.
  22nd Annual Conference on Learning Theory (COLT 2009).
  

• Stochastic Convex Optimization
  Shai Shalev-Shwartz, Ohad Shamir, Nathan Srebro and Karthik Sridharan.
  22nd Annual Conference on Learning Theory (COLT 2009).
  

• Good Learners for Evil Teachers
  Ofer Dekel and Ohad Shamir.
  26th International Conference on Machine Learning (ICML 2009).
  

• On the Reliability of Clustering Stability in the Large Sample Regime
  Ohad Shamir and Naftali Tishby.
  22nd Annual Conference on Neural Information Processing Systems (NIPS 2008).
  
  • Supplementary material

• Learning and Generalization with the Information Bottleneck
  Ohad Shamir, Sivan Sabato and Naftali Tishby.
  19th International Conference on Algorithmic Learning Theory (ALT 2008).
  
  • Version with all the proofs

• Model Selection and Stability in k-means Clustering
  Ohad Shamir and Naftali Tishby.
  21st Annual Conference on Learning Theory (COLT 2008).
  

• Learning to Classify with Missing and Corrupted Features
  Ofer Dekel and Ohad Shamir.
  25th International Conference on Machine Learning (ICML 2008).

• Cluster Stability for Finite Samples
  Ohad Shamir and Naftali Tishby.
  21st Annual Conference on Neural Information Processing Systems (NIPS 2007).
  
  • Supplementary material

Other Publications and Misc.

• A Variant of Azuma's Inequality for Martingales with Subgaussian Tails
  Ohad Shamir.
  A small note on how to apply a concentration inequality for martingales which are only bounded in high probability.

• Agnostically Learning Halfspaces with Margin Errors
  Shai Shalev-Shwartz, Ohad Shamir and Karthik Sridharan.
  TTI-C Technical Report, June 2009

• The Complexity of Improperly Learning Large Margin Halfspaces
  Shai Shalev-Shwartz, Ohad Shamir and Karthik Sridharan.
  Open problem presented in the 22nd Annual Conference on Learning Theory (COLT 2009).

Teaching

• TA in Introduction to Information Theory, 2008-2009
• TA In Introduction to Machine Learning, 2009-2010

Misc.

Hobbies