How to use expert advice
@article{CesaBianchi1997HowTU, title={How to use expert advice}, author={N. Cesa-Bianchi and Y. Freund and D. Haussler and D. Helmbold and R. Schapire and Manfred K. Warmuth}, journal={J. ACM}, year={1997}, volume={44}, pages={427-485} }
We analyze algorithms that predict a binary value by combining the predictions of several prediction strategies, called experts. Our analysis is for worst-case situations, i.e., we make no assumptions about the way the sequence of bits to be predicted is generated. We measure the performance of the algorithm by the difference between the expected number of mistakes it makes on the bit sequence and the expected number of mistakes made by the best expert on this sequence, where the expectation is… CONTINUE READING
208 Citations
Lipschitz Adaptivity with Multiple Learning Rates in Online Learning
- Computer Science, Mathematics
- COLT
- 2019
- 7
- Highly Influenced
- PDF
Tight Lower Bounds for the Multiplicative Weights Algorithm on the Experts Problem
- 2015
- Highly Influenced
- PDF
On delayed prediction of individual sequences
- Mathematics, Computer Science
- IEEE Trans. Inf. Theory
- 2002
- 31
- Highly Influenced
- PDF
Genral Linear Relations among Different Types of Predictive Complexity
- Mathematics, Computer Science
- ALT
- 1999
- 13
- Highly Influenced
The robustness of the p-norm algorithms
- Mathematics, Computer Science
- COLT '99
- 1999
- 139
- Highly Influenced
Online Submodular Maximization under a Matroid Constraint with Application to Learning Assignments
- Computer Science
- ArXiv
- 2014
- 24
- Highly Influenced
- PDF