Learning Theory

1. The spectral method for general mixture models* (R. Kannan and H. Salmasian)
   Proc. of the 18th Conference on Learning Theory, 2005.
   
2. On Kernels, Margins and Low-dimensional Mappings. (Nina Balcan, Avrim Blum)
   Proc. of the 15th Conf. Algorithmic Learning Theory, Padua, 2004.
   To appear in Machine Learning.
   
3. Efficient algorithms for the online decision problem. (Adam Kalai)
   Proc. of 16th Conf. on Computational Learning Theory, Washington D.C., 2003.
   
4. A spectral algorithm for learning mixtures of distributions*. (Grant Wang)
   Proc. of the 43rd IEEE Foundations of Computer Science (FOCS '02), Vancouver, 2002.
   JCSS (special issue for FOCS '02), 68(4), 841--860, 2004.
   
5. Optimal outlier removal in high-dimensional spaces. (John Dunagan)
   Proc. of the 33rd ACM Symposium on the Theory of Computing (STOC '01), Crete, 2001.
   JCSS (special issue for STOC '01), 68(2), 335--373, 2004.
   
6. An algorithmic theory of learning: Robust Concepts and Random Projection. (Rosa I. Arriaga)
   Proc. of the 40th Foundations of Computer Science (FOCS '99), New York, 1999.
   To appear in Machine Learning.
   
7. A Random Sampling based Algorithm for learning the Intersection of Half-spaces
   Proc. of the 38th Foundations of Computer Science (FOCS '97), Miami, 1997. (Machtey Prize)
   
8. A Polynomial-Time Algorithm for Learning Noisy Linear Threshold Functions.
   (Avrim Blum, Alan Frieze and Ravi Kannan)
   Proc. 37th IEEE Symposium on the Foundations of Computer Science (FOCS '96), Burlington, 1996.
   Algorithmica, 22(1), 35-52 (invited).
   

(* also appears under "Spectral methods and IR".)