Mistake bounds and logarithmic linear-threshold learning algorithms
Mistake bounds and logarithmic linear-threshold learning algorithms
Elements of information theory
Elements of information theory
The weighted majority algorithm
Information and Computation
A dynamic disk spin-down technique for mobile computing
MobiCom '96 Proceedings of the 2nd annual international conference on Mobile computing and networking
Exponentiated gradient versus gradient descent for linear predictors
Information and Computation
Journal of the ACM (JACM)
Using and combining predictors that specialize
STOC '97 Proceedings of the twenty-ninth annual ACM symposium on Theory of computing
A decision-theoretic generalization of on-line learning and an application to boosting
Journal of Computer and System Sciences - Special issue: 26th annual ACM symposium on the theory of computing & STOC'94, May 23–25, 1994, and second annual Europe an conference on computational learning theory (EuroCOLT'95), March 13–15, 1995
Derandomizing stochastic prediction strategies
COLT '97 Proceedings of the tenth annual conference on Computational learning theory
On-line learning and the metrical task system problem
COLT '97 Proceedings of the tenth annual conference on Computational learning theory
A game of prediction with expert advice
Journal of Computer and System Sciences - Special issue on the eighth annual workshop on computational learning theory, July 5–8, 1995
Machine Learning - Special issue on context sensitivity and concept drift
Sequential prediction of individual sequences under general loss functions
IEEE Transactions on Information Theory
COLT' 98 Proceedings of the eleventh annual conference on Computational learning theory
Machine Learning - Special issue on context sensitivity and concept drift
Learning specialist decision lists
COLT '99 Proceedings of the twelfth annual conference on Computational learning theory
On-line Learning and the Metrical Task System Problem
Machine Learning
Probability theory for the Brier game
Theoretical Computer Science
Tracking a Small Set of Experts by Mixing Past Posteriors
COLT '01/EuroCOLT '01 Proceedings of the 14th Annual Conference on Computational Learning Theory and and 5th European Conference on Computational Learning Theory
A Second-Order Perceptron Algorithm
COLT '02 Proceedings of the 15th Annual Conference on Computational Learning Theory
Tracking Linear-Threshold Concepts with Winnow
COLT '02 Proceedings of the 15th Annual Conference on Computational Learning Theory
FOCS '99 Proceedings of the 40th Annual Symposium on Foundations of Computer Science
Tracking the best linear predictor
The Journal of Machine Learning Research
Tracking a small set of experts by mixing past posteriors
The Journal of Machine Learning Research
Using confidence bounds for exploitation-exploration trade-offs
The Journal of Machine Learning Research
The Robustness of the p-Norm Algorithms
Machine Learning
Tracking linear-threshold concepts with Winnow
The Journal of Machine Learning Research
Using additive expert ensembles to cope with concept drift
ICML '05 Proceedings of the 22nd international conference on Machine learning
Can machine learning be secure?
ASIACCS '06 Proceedings of the 2006 ACM Symposium on Information, computer and communications security
Diverse committees vote for dependable profits
Proceedings of the 9th annual conference on Genetic and evolutionary computation
Tracking the best hyperplane with a simple budget Perceptron
Machine Learning
Foundations and Trends in Databases
Dynamic Weighted Majority: An Ensemble Method for Drifting Concepts
The Journal of Machine Learning Research
Markov Decision Processes with Arbitrary Reward Processes
Recent Advances in Reinforcement Learning
Efficient learning algorithms for changing environments
ICML '09 Proceedings of the 26th Annual International Conference on Machine Learning
Piecewise-stationary bandit problems with side observations
ICML '09 Proceedings of the 26th Annual International Conference on Machine Learning
Boosting expert ensembles for rapid concept recall
AAAI'06 Proceedings of the 21st national conference on Artificial intelligence - Volume 1
Markov Decision Processes with Arbitrary Reward Processes
Mathematics of Operations Research
An experts algorithm for transfer learning
IJCAI'07 Proceedings of the 20th international joint conference on Artifical intelligence
Discrete denoising with shifts
IEEE Transactions on Information Theory
Learning Permutations with Exponential Weights
The Journal of Machine Learning Research
Expert mixture methods for adaptive channel equalization
ICANN/ICONIP'03 Proceedings of the 2003 joint international conference on Artificial neural networks and neural information processing
λ-Perceptron: An adaptive classifier for data streams
Pattern Recognition
Competitive online generalized linear regression under square loss
ECML PKDD'10 Proceedings of the 2010 European conference on Machine learning and knowledge discovery in databases: Part III
ALT'10 Proceedings of the 21st international conference on Algorithmic learning theory
Prediction with expert advice under discounted loss
ALT'10 Proceedings of the 21st international conference on Algorithmic learning theory
A regularization approach to metrical task systems
ALT'10 Proceedings of the 21st international conference on Algorithmic learning theory
On upper-confidence bound policies for switching bandit problems
ALT'11 Proceedings of the 22nd international conference on Algorithmic learning theory
Combining initial segments of lists
ALT'11 Proceedings of the 22nd international conference on Algorithmic learning theory
The shortest path problem under partial monitoring
COLT'06 Proceedings of the 19th annual conference on Learning Theory
Tracking the best hyperplane with a simple budget perceptron
COLT'06 Proceedings of the 19th annual conference on Learning Theory
COLT'06 Proceedings of the 19th annual conference on Learning Theory
Continuous experts and the binning algorithm
COLT'06 Proceedings of the 19th annual conference on Learning Theory
Tracking the best of many experts
COLT'05 Proceedings of the 18th annual conference on Learning Theory
Minimum delay load-balancing via nonparametric regression and no-regret algorithms
Computer Networks: The International Journal of Computer and Telecommunications Networking
A learning-based approach to reactive security
FC'10 Proceedings of the 14th international conference on Financial Cryptography and Data Security
Linear programming with online learning
Operations Research Letters
Traffic-aware techniques to reduce 3G/LTE wireless energy consumption
Proceedings of the 8th international conference on Emerging networking experiments and technologies
New analysis and algorithm for learning with drifting distributions
ALT'12 Proceedings of the 23rd international conference on Algorithmic Learning Theory
A closer look at adaptive regret
ALT'12 Proceedings of the 23rd international conference on Algorithmic Learning Theory
Theoretical Computer Science
On ensemble techniques for AIXI approximation
AGI'12 Proceedings of the 5th international conference on Artificial General Intelligence
On evaluating stream learning algorithms
Machine Learning
Online learning with multiple kernels: A review
Neural Computation
Online portfolio selection: A survey
ACM Computing Surveys (CSUR)
A survey on concept drift adaptation
ACM Computing Surveys (CSUR)
Combining initial segments of lists
Theoretical Computer Science
| Hi-index | 0.06 |
We generalize the recent relative loss bounds for on-line algorithms where the additional loss of the algorithm on the whole sequence of examples over the loss of the best expert is bounded. The generalization allows the sequence to be partitioned into segments, and the goal is tobound the additional loss of the algorithm over the sum of the losses ofthe best experts for each segment. This is to model situations in which theexamples change and different experts are best for certain segments of thesequence of examples. In the single segment case, the additional loss isproportional to log n, where n is the number ofexperts and the constant of proportionality depends on the loss function.Our algorithms do not produce the best partition; however the loss boundshows that our predictions are close to those of the best partition. Whenthe number of segments is k+1 and the sequence is of lengthℓ, we can bound the additional loss of our algorithm over the bestpartition by O(k \log n+k \log(ℓ/k)). For thecase when the loss per trial is bounded by one, we obtain an algorithmwhose additional loss over the loss of the best partition is independent ofthe length of the sequence. The additional loss becomes O(k\log n+ k\log(L/k)), where L is the loss of the bestpartitionwith k+1 segments. Our algorithms for tracking thepredictions of the best expert aresimple adaptations of Vovk'soriginal algorithm for the single best expert case. As in the originalalgorithms, we keep one weight per expert, and spend O(1) timeper weight in each trial.