ALT 2006 - PDF Preprint Papers

ALT 2006 Algorithmic Learning Theory

Teaser Browsing | Click Here

Title Browsing | Click Here

Wall of Fame | Most Viewed ALT-2006 Paper

click to vote

ALT
2006
Springer

156views Machine Learning» more ALT 2006»

Hannan Consistency in On-Line Learning in Case of Unbounded Losses Under Partial Monitoring

13 years 8 months ago

Download www.szit.bme.hu

In this paper the sequential prediction problem with expert advice is considered when the loss is unbounded under partial monitoring scenarios. We deal with a wide class of the par...

Chamy Allenberg, Peter Auer, László ...

claim paper

Read More »

Disclaimer and Copyright Notice

Sciweavers respects the rights of all copyright holders and in this regard, authors are only allowed to share a link to their preprint paper on their own website. Every contribution is associated with a desciptive image. It is the sole responsibility of the authors to ensure that their posted image is not copyright infringing. This service is compliant with IEEE copyright.

Id	Views	Title	Status

1	156	Hannan Consistency in On-Line Learning in Case of Unbounded Losses Under Partial Monitoring	claim
2	146	Probabilistic Generalization of Simple Grammars and Its Application to Reinforcement Learning	claim
3	139	How Many Query Superpositions Are Needed to Learn?	claim
4	137	Large-Margin Thresholded Ensembles for Ordinal Regression: Theory and Practice	claim
5	136	Active Learning in the Non-realizable Case	claim
6	121	On Exact Learning from Random Walk	claim
7	119	Smooth Boosting Using an Information-Based Criterion	claim
8	115	e-Science and the Semantic Web: A Symbiotic Relationship	claim
9	115	Learning Linearly Separable Languages	claim
10	115	Leading Strategies in Competitive On-Line Prediction	claim
11	111	Asymptotic Learnability of Reinforcement Problems with Arbitrary Dependence	claim
12	109	General Discounting Versus Average Reward	claim
13	108	Solving Semi-infinite Linear Programs Using Boosting-Like Methods	claim
14	105	On Exact Learning Halfspaces with Random Consistent Hypothesis Oracle	claim
15	104	Iterative Learning from Positive Data and Negative Counterexamples	claim
16	103	Unsupervised Slow Subspace-Learning from Stationary Processes	claim
17	101	Teaching Memoryless Randomized Learners Without Feedback	claim
18	98	Learning and Extending Sublanguages	claim
19	94	Is There an Elegant Universal Theory of Prediction?	claim
20	90	Towards a Better Understanding of Incremental Learning	claim
21	86	Risk-Sensitive Online Learning	claim
22	78	The Complexity of Learning SUBSEQ (A)	claim

Sciweavers

Explore & Download

Productivity Tools

Document Tools

Image Tools

Sciweavers