The weighted majority algorithm
Information and Computation
Exponentiated gradient versus gradient descent for linear predictors
Information and Computation
Journal of the ACM (JACM)
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
Combinatorial Information Market Design
Information Systems Frontiers
A dynamic pari-mutuel market for hedging, wagering, and information aggregation
EC '04 Proceedings of the 5th ACM conference on Electronic commerce
Adaptive Online Prediction by Following the Perturbed Leader
The Journal of Machine Learning Research
Efficient algorithms for online decision problems
Journal of Computer and System Sciences - Special issue: Learning theory 2003
Logarithmic regret algorithms for online convex optimization
Machine Learning
A primal-dual perspective of online learning algorithms
Machine Learning
Pricing combinatorial markets for tournaments
STOC '08 Proceedings of the fortieth annual ACM symposium on Theory of computing
Eliciting properties of probability distributions
Proceedings of the 9th ACM conference on Electronic commerce
Complexity of combinatorial market makers
Proceedings of the 9th ACM conference on Electronic commerce
Surrogate regret bounds for proper losses
ICML '09 Proceedings of the 26th Annual International Conference on Machine Learning
A unified framework for dynamic pari-mutuel information market design
Proceedings of the 10th ACM conference on Electronic commerce
WINE '09 Proceedings of the 5th International Workshop on Internet and Network Economics
Learning Permutations with Exponential Weights
The Journal of Machine Learning Research
An axiomatic characterization of continuous-outcome market makers
WINE'10 Proceedings of the 6th international conference on Internet and network economics
Connections between markets and learning
ACM SIGecom Exchanges
An optimization-based framework for automated market-making
Proceedings of the 12th ACM conference on Electronic commerce
Information market based recommender systems fusion
Proceedings of the 2nd International Workshop on Information Heterogeneity and Fusion in Recommender Systems
Liquidity-sensitive automated market makers via homogeneous risk measures
WINE'11 Proceedings of the 7th international conference on Internet and Network Economics
Proceedings of the 13th ACM Conference on Electronic Commerce
An efficient Monte-Carlo algorithm for pricing combinatorial prediction markets for tournaments
IJCAI'11 Proceedings of the Twenty-Second international joint conference on Artificial Intelligence - Volume Volume One
Efficient Market Making via Convex Optimization, and a Connection to Online Learning
ACM Transactions on Economics and Computation - Special Issue on Algorithmic Game Theory
An axiomatic characterization of adaptive-liquidity market makers
Proceedings of the fourteenth ACM conference on Electronic commerce
Cost function market makers for measurable spaces
Proceedings of the fourteenth ACM conference on Electronic commerce
An introduction to artificial prediction markets for classification
The Journal of Machine Learning Research
A Practical Liquidity-Sensitive Automated Market Maker
ACM Transactions on Economics and Computation
Hi-index | 0.00 |
We explore the striking mathematical connections that exist between market scoring rules, cost function based prediction markets, and no-regret learning. We first show that any cost function based prediction market can be interpreted as an algorithm for the commonly studied problem of learning from expert advice by equating the set of outcomes on which bets are placed in the market with the set of experts in the learning setting, and equating trades made in the market with losses observed by the learning algorithm. If the loss of the market organizer is bounded, this bound can be used to derive an O(√T) regret bound for the corresponding learning algorithm. We then show that the class of markets with convex cost functions exactly corresponds to the class of Follow the Regularized Leader learning algorithms, with the choice of a cost function in the market corresponding to the choice of a regularizer in the learning problem. Finally, we show an equivalence between market scoring rules and prediction markets with convex cost functions. This implies both that any market scoring rule can be implemented as a cost function based market maker, and that market scoring rules can be interpreted naturally as Follow the Regularized Leader algorithms. These connections provide new insight into how it is that commonly studied markets, such as the Logarithmic Market Scoring Rule, can aggregate opinions into accurate estimates of the likelihood of future events.