Amortized efficiency of list update and paging rules
Communications of the ACM
Self-adjusting binary search trees
Journal of the ACM (JACM)
Journal of Algorithms
From on-line to batch learning
COLT '89 Proceedings of the second annual workshop on Computational learning theory
Predicting Nearly As Well As the Best Pruning of a Decision Tree
Machine Learning - Special issue on the eighth annual conference on computational learning theory, (COLT '95)
Using and combining predictors that specialize
STOC '97 Proceedings of the twenty-ninth annual ACM symposium on Theory of computing
Approximating the bandwidth via volume respecting embeddings (extended abstract)
STOC '98 Proceedings of the thirtieth annual ACM symposium on Theory of computing
Polynomial time approximation schemes for Euclidean traveling salesman and other geometric problems
Journal of the ACM (JACM)
Small distortion and volume preserving embeddings for planar and Euclidean metrics
SCG '99 Proceedings of the fifteenth annual symposium on Computational geometry
Approximation algorithms
Predicting nearly as well as the best pruning of a planar decision graph
Theoretical Computer Science
On Euclidean Embeddings and Bandwidth Minimization
APPROX '01/RANDOM '01 Proceedings of the 4th International Workshop on Approximation Algorithms for Combinatorial Optimization Problems and 5th International Workshop on Randomization and Approximation Techniques in Computer Science: Approximation, Randomization and Combinatorial Optimization
FOCS '99 Proceedings of the 40th Annual Symposium on Foundations of Computer Science
Adapting to a reliable network path
Proceedings of the twenty-second annual symposium on Principles of distributed computing
Path kernels and multiplicative updates
The Journal of Machine Learning Research
Adaptive routing with end-to-end feedback: distributed learning and geometric approaches
STOC '04 Proceedings of the thirty-sixth annual ACM symposium on Theory of computing
Approximation algorithms and online mechanisms for item pricing
EC '06 Proceedings of the 7th ACM conference on Electronic commerce
Algorithms for portfolio management based on the Newton method
ICML '06 Proceedings of the 23rd international conference on Machine learning
Proceedings of the twenty-fifth annual ACM symposium on Principles of distributed computing
Perspectives on multiagent learning
Artificial Intelligence
Playing games with approximation algorithms
Proceedings of the thirty-ninth annual ACM symposium on Theory of computing
Online discovery of similarity mappings
Proceedings of the 24th international conference on Machine learning
Logarithmic regret algorithms for online convex optimization
Machine Learning
Online linear optimization and adaptive routing
Journal of Computer and System Sciences
Regret based dynamics: convergence in weakly acyclic games
Proceedings of the 6th international joint conference on Autonomous agents and multiagent systems
Nonstochastic bandits: Countable decision set, unbounded costs and reactive environments
Theoretical Computer Science
Regret to the best vs. regret to the average
Machine Learning
Rank minimization via online learning
Proceedings of the 25th international conference on Machine learning
Following the Perturbed Leader to Gamble at Multi-armed Bandits
ALT '07 Proceedings of the 18th international conference on Algorithmic Learning Theory
Markov Decision Processes with Arbitrary Reward Processes
Recent Advances in Reinforcement Learning
Online Markov Decision Processes
Mathematics of Operations Research
Markov Decision Processes with Arbitrary Reward Processes
Mathematics of Operations Research
Route planning under uncertainty: the Canadian traveller problem
AAAI'08 Proceedings of the 23rd national conference on Artificial intelligence - Volume 2
Computing equilibria in multiplayer stochastic games of imperfect information
IJCAI'09 Proceedings of the 21st international jont conference on Artifical intelligence
Online learning in Markov decision processes with arbitrarily changing rewards and transitions
GameNets'09 Proceedings of the First ICST international conference on Game Theory for Networks
Regret Minimization and Job Scheduling
SOFSEM '10 Proceedings of the 36th Conference on Current Trends in Theory and Practice of Computer Science
Learning Permutations with Exponential Weights
The Journal of Machine Learning Research
Regret to the best vs. regret to the average
COLT'07 Proceedings of the 20th annual conference on Learning theory
Learning permutations with exponential weights
COLT'07 Proceedings of the 20th annual conference on Learning theory
Multitask learning with expert advice
COLT'07 Proceedings of the 20th annual conference on Learning theory
Differential privacy under continual observation
Proceedings of the forty-second ACM symposium on Theory of computing
A new understanding of prediction markets via no-regret learning
Proceedings of the 11th ACM conference on Electronic commerce
The follow perturbed leader algorithm protected from unbounded one-step losses
ALT'09 Proceedings of the 20th international conference on Algorithmic learning theory
Learning volatility of discrete time series using prediction with expert advice
SAGA'09 Proceedings of the 5th international conference on Stochastic algorithms: foundations and applications
Online algorithms for the newsvendor problem with and without censored demands
FAW'10 Proceedings of the 4th international conference on Frontiers in algorithmics
Approximation algorithms for reliable stochastic combinatorial optimization
APPROX/RANDOM'10 Proceedings of the 13th international conference on Approximation, and 14 the International conference on Randomization, and combinatorial optimization: algorithms and techniques
Network-wide deployment of intrusion detection and prevention systems
Proceedings of the 6th International COnference
Online Learning in Case of Unbounded Losses Using Follow the Perturbed Leader Algorithm
The Journal of Machine Learning Research
GSP auctions with correlated types
Proceedings of the 12th ACM conference on Electronic commerce
Proceedings of the forty-third annual ACM symposium on Theory of computing
Meta optimization and its application to portfolio selection
Proceedings of the 17th ACM SIGKDD international conference on Knowledge discovery and data mining
Better Algorithms for Benign Bandits
The Journal of Machine Learning Research
Adaptive Subgradient Methods for Online Learning and Stochastic Optimization
The Journal of Machine Learning Research
Combining initial segments of lists
ALT'11 Proceedings of the 22nd international conference on Algorithmic learning theory
Online Optimization with Uncertain Information
ACM Transactions on Algorithms (TALG)
Logarithmic regret algorithms for online convex optimization
COLT'06 Proceedings of the 19th annual conference on Learning Theory
Quasi-proportional mechanisms: prior-free revenue maximization
LATIN'10 Proceedings of the 9th Latin American conference on Theoretical Informatics
Optimum follow the leader algorithm
COLT'05 Proceedings of the 18th annual conference on Learning Theory
Online Learning and Online Convex Optimization
Foundations and Trends® in Machine Learning
Journal of Computer and System Sciences
Randomized sensing in adversarial environments
IJCAI'11 Proceedings of the Twenty-Second international joint conference on Artificial Intelligence - Volume Volume Three
Online prediction under submodular constraints
ALT'12 Proceedings of the 23rd international conference on Algorithmic Learning Theory
Lower bounds on individual sequence regret
ALT'12 Proceedings of the 23rd international conference on Algorithmic Learning Theory
New algorithms for budgeted learning
Machine Learning
Online Multiple Kernel Classification
Machine Learning
Online submodular minimization
The Journal of Machine Learning Research
Combining initial segments of lists
Theoretical Computer Science
Hi-index | 0.00 |
In an online decision problem, one makes a sequence of decisions without knowledge of the future. Each period, one pays a cost based on the decision and observed state. We give a simple approach for doing nearly as well as the best single decision, where the best is chosen with the benefit of hindsight. A natural idea is to follow the leader, i.e. each period choose the decision which has done best so far. We show that by slightly perturbing the totals and then choosing the best decision, the expected performance is nearly as good as the best decision in hindsight. Our approach, which is very much like Hannan's original game-theoretic approach from the 1950s, yields guarantees competitive with the more modern exponential weighting algorithms like Weighted Majority. More importantly, these follow-the-leader style algorithms extend naturally to a large class of structured online problems for which the exponential algorithms are inefficient.