Mistake bounds and logarithmic linear-threshold learning algorithms
Mistake bounds and logarithmic linear-threshold learning algorithms
The perception: a probabilistic model for information storage and organization in the brain
Neurocomputing: foundations of research
Exponentiated gradient versus gradient descent for linear predictors
Information and Computation
Relative Loss Bounds for Multidimensional Regression Problems
Machine Learning
Parallel Optimization: Theory, Algorithms and Applications
Parallel Optimization: Theory, Algorithms and Applications
General Convergence Results for Linear Discriminant Updates
Machine Learning
The Relaxed Online Maximum Margin Algorithm
Machine Learning
A new approximate maximal margin classification algorithm
The Journal of Machine Learning Research
The Robustness of the p-Norm Algorithms
Machine Learning
Convex Optimization
A Second-Order Perceptron Algorithm
SIAM Journal on Computing
IEEE Transactions on Signal Processing
Relative loss bounds for single neurons
IEEE Transactions on Neural Networks
Efficient bandit algorithms for online multiclass prediction
Proceedings of the 25th international conference on Machine learning
Sequence Labelling SVMs Trained in One Pass
ECML PKDD '08 Proceedings of the 2008 European Conference on Machine Learning and Knowledge Discovery in Databases - Part I
A new understanding of prediction markets via no-regret learning
Proceedings of the 11th ACM conference on Electronic commerce
Towards the randomized k-server conjecture: a primal-dual approach
SODA '10 Proceedings of the twenty-first annual ACM-SIAM symposium on Discrete Algorithms
Tuning metaheuristics: A data mining based approach for particle swarm optimization
Expert Systems with Applications: An International Journal
Two one-pass algorithms for data stream classification using approximate MEBs
ICANNGA'11 Proceedings of the 10th international conference on Adaptive and natural computing algorithms - Volume Part II
Double Updating Online Learning
The Journal of Machine Learning Research
Metric learning for reinforcement learning agents
The 10th International Conference on Autonomous Agents and Multiagent Systems - Volume 2
Online Learning and Online Convex Optimization
Foundations and Trends® in Machine Learning
Liquidity-sensitive automated market makers via homogeneous risk measures
WINE'11 Proceedings of the 7th international conference on Internet and Network Economics
Regularization techniques for learning with matrices
The Journal of Machine Learning Research
Robust tracking with weighted online structured learning
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part III
Online learning with multiple kernels: A review
Neural Computation
Efficient Market Making via Convex Optimization, and a Connection to Online Learning
ACM Transactions on Economics and Computation - Special Issue on Algorithmic Game Theory
Efficient online learning for multitask feature selection
ACM Transactions on Knowledge Discovery from Data (TKDD)
| Hi-index | 0.00 |
We describe a novel framework for the design and analysis of online learning algorithms based on the notion of duality in constrained optimization. We cast a sub-family of universal online bounds as an optimization problem. Using the weak duality theorem we reduce the process of online learning to the task of incrementally increasing the dual objective function. The amount by which the dual increases serves as a new and natural notion of progress for analyzing online learning algorithms. We are thus able to tie the primal objective value and the number of prediction mistakes using the increase in the dual.