Online Bounds for Bayesian Algorithms

By Sham M. Kakade, Andrew Y. Ng. 2004

65 citations recorded by the source corpus.

Subfields: Probabilistic & Bayesian Methods, Statistical Learning Theory

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Probabilistic & Bayesian Methods

1. Arindam Banerjee
2. Vladimir G Vovk
3. Nicolò Cesa-Bianchi
4. Pieter Abbeel
5. Gábor Lugosi
6. Andrew Y. Ng
7. Sergey Levine
8. Stefano Ermon

In Statistical Learning Theory

1. Pieter Abbeel
2. Gábor Lugosi
3. Arindam Banerjee
4. Vladimir G Vovk
5. Nicolò Cesa-Bianchi
6. Andrew Y. Ng
7. Aaditya Ramdas
8. E.J. Candes

Citations in the corpus

• Kernel Ridge Regression (2013, background): “1 of [8], which has an additional regret term of the logarithmic order in time.”
• On Bayesian bounds (2006, background): “Theorem 2 (Log Loss Bound) In the Bayesian log-loss setting, for any distribution Q on H , we have The result has appeared in different forms in the literature (Freund et al., 1997; Kakade & Ng, 2004).”
• Prediction, learning, and games (2006, background): “10 was proved by Kakade and Ng [173].”
• Exploration and apprenticeship learning in reinforcement learning (2005, background): “Note that Kakade and Ng (2005) give results for generalized linear models.”