Research
Publications
| [1] | Ambuj Tewari and Peter L. Bartlett.
Optimistic linear programming gives logarithmic regret for
irreducible MDPs.
In Advances in Neural Information Processing Systems 20. MIT
Press, 2008.
to appear. [ bib | .pdf ] |
| [2] | Ambuj Tewari and Peter L. Bartlett.
Bounded parameter Markov decision processes with average reward
criterion.
In Proceedings of the 20th Annual Conference on Learning
Theory, volume 4539 of Lecture Notes in Computer Science, pages
263-277. Springer, 2007. [ bib | http | .pdf ] |
| [3] | Ambuj Tewari and Peter L. Bartlett.
On the consistency of multiclass classification methods.
Journal of Machine Learning Research, 8:1007-1025, May 2007.
(Invited paper). [ bib | .html | .pdf ] |
| [4] | Peter L. Bartlett and Ambuj Tewari.
Sparseness vs estimating conditional probabilities: Some asymptotic
results.
Journal of Machine Learning Research, 8:775-790, Apr 2007. [ bib | .html | .pdf ] |
| [5] | Peter L. Bartlett and Ambuj Tewari.
Sample complexity of policy search with known dynamics.
In Advances in Neural Information Processing Systems 19, pages
97-104. MIT Press, 2007. [ bib | .html | .pdf ] |
| [6] | Ambuj Tewari and Peter L. Bartlett.
On the consistency of multiclass classification methods.
In Proceedings of the 18th Annual Conference on Learning
Theory, volume 3559 of Lecture Notes in Computer Science, pages
147-153. Springer, 2005.
Student Paper Award. [ bib | http | .pdf ] |
| [7] | Peter L. Bartlett and Ambuj Tewari.
Sparseness versus estimating conditional probabilities: Some
asymptotic results.
In Proceedings of the 17th Annual Conference on Learning
Theory, volume 3120 of Lecture Notes in Computer Science, pages
564-578. Springer, 2004. [ bib | http | .pdf ] |
| [8] | Ambuj Tewari, Utkarsh Srivastava, and Phalguni Gupta.
A parallel DFA minimization algorithm.
In Proceedings of the 9th International Conference on High
Performance Computing, volume 2552 of Lecture Notes in Computer
Science, pages 34-40. Springer, 2002. [ bib | http | .pdf ] |
Theses
| [1] | Ambuj Tewari.
Reinforcement Learning in Large or Unknown MDPs.
PhD dissertation, University of California at Berkeley, Department
of Electrical Engineering and Computer Sciences, 2007. [ bib | .pdf ] |
| [2] | Ambuj Tewari.
On the Consistency of Multiclass Classification Methods.
MA thesis, University of California at Berkeley, Department of
Statistics, 2005. [ bib | .pdf ] |