General PAC-Bayes:

Some PAC-Bayesian theorems COLT, 1998

PAC-Bayesian model averaging COLT, 1999

PAC-Bayesian stochastic model selection Journal of Machine Learning, 2003.

Simplified PAC-Bayesian margin bounds, COLT, 2003.

Anyone Interested in Learning about PAC-Bayes Generalization Theory should go directory to the following tutorial

A PAC-Bayesian Tutorial with a Dropout Bound, ArXive1307.2118, July, 2013


Approximate planning for factored POMDPs using belief state simplification with Satinder Singh, UAI, 1996.

Policy Gradient Methods for Reinforcement Learning with Function Approximation with Yishai Mansaur, Rich Sutton, and Satinder Singh, NIPS, 1999.

Generalization Bounds for Decision Trees with Yishai Mansour, COLT, 2000.

On the Convergence Rate of Good-Turing Estimators with Rob Schapire, COLT, 2000.

Boosting using branching programs with Yishai Mansour, COLT, 2000

Computable Shell Decomposition Bounds with John Langford, COLT, 2000

Hardening Soft Information Sources with Henry Kautz and William Cohen, KDD, 2000.

PAC Generalization Bounds for Co-Training with Sanjoy Dasgupta, NIPS,2002.

Concentration inequalities for the missing mass and for histogram rule error with Luis Ortiz, Journal of Artificial Intelligence Research (JAIR) 2003.

Case-factor diagrams for structured probabilistic modeling with Michael Collins and Fernando Pereira, UAI, 2004.

Affine algebraic decision diagrams (AADDs) and their application to structured probabilistic inference with Scott Sanner, IJCAI, 2005.

Exponentiated gradient algorithms for large-margin structured classification with Peter Bartlett, Michael Collins and Ben Taskar, NIPS, 2005

Maximum margin semi-supervised learning for structured variables with Yasemin Altun and Misha Belkan, NIPS, 2005.

Generalization bounds and consistency for structured labeling paper available from 2006, finally appeared in the collection "Predicting Structured Data" from MIT Press, 2009.

Particle belief propagation with Alex Ihler, AISTATS, 2009.

Direct loss minimization for structured prediction with Yoseph Keshet, NIPS, 2010.

Generalization Bounds and Consistency for Latent Structural Probit and Ramp Loss with Joseph Keshet, NIPS 2011.

Pac-bayesian approach for minimization of phoneme error rate with Joseph Keshet and Tamir Hazan, ICASP, 2011.