Seminar on Learning Theory and Optimization (2017)

Slides

1. Statistical Learning Theory
   Reference: Bousquet et al. Introduction to Statistical Learning Theory. In Advanced Lectures on Machine Learning, 169-207, 2004.
   
   
2. Convex Optimization
   Reference: Boyd and Vandenberghe. Convex Optimization. Cambridge University Press, 2004.
   
   
3. Stochastic Optimization
   Reference: Hazan and Kale. Beyond the regret minimization barrier: an optimal algorithm for stochastic strongly-convex optimization. In COLT, 421-436, 2011.
   
   
4. Full-information Online Learning
   Reference: Zinkevich. Online convex programming and generalized infinitesimal gradient ascent. In ICML, 928-936, 2003.
                     Hazan et al. Logarithmic regret algorithms for online convex optimization. Machine Learning, 69(2-3):169-192, 2007.
   
   
5. Bandit Online Learning
   Reference: Auer et al. Finite-time analysis of the multiarmed bandit problem. Machine Learning, 47(2-3):235-256, 2002.
                     Abbasi-yadkori et al. Improved algorithms for linear stochastic bandits. In NIPS, 2312-2320, 2011.