The Internet Archive has a preservation copy of this work in our general collections.
The file type is application/pdf.
Filters
Prediction with Expert Advice by Following the Perturbed Leader for General Weights
[article]
2004
arXiv
pre-print
Preserved Fulltext
Other Versions
When applying aggregating strategies to Prediction with Expert Advice, the learning rate must be adaptively tuned. ...
The analysis of the alternative "Follow the Perturbed Leader" (FPL) algorithm from Kalai (2003} (based on Hannan's algorithm) is easier. ...
Prediction with Expert Advice proceeds as follows. We are asked to perform sequential predictions y t ∈ Y at times t = 1,2,.... ...
arXiv:cs/0405043v2
fatcat:yudoctlpjzdlhjs6zvapnbnble
Prediction with Expert Advice by Following the Perturbed Leader for General Weights
[chapter]
2004
Lecture Notes in Computer Science
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2016; you can also visit the original URL.
The file type is application/pdf.
Keywords Prediction with Expert Advice, Follow the Perturbed Leader, general weights, adaptive learning rate, hierarchy of experts, expected and high probability bounds, general alphabet and loss, online ...
The theory of Prediction with Expert Advice (PEA) has rapidly developed in the recent past. ...
Prediction with Expert Advice proceeds as follows. We are asked to perform sequential predictions y t ∈ Y at times t = 1,2,.... ...
doi:10.1007/978-3-540-30215-5_22
fatcat:4y6k44uze5c4dpvq4kdg4owjry
Move from Perturbed scheme to exponential weighting average
[article]
2015
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Finally, we show with some examples that follow-the-leader style algorithms extend naturally to a large class of structured online problems for which the exponential algorithms are inefficient. ...
However, recently, another algorithm called follow the perturbed leader is developed and achieved about the same performance. ...
Conclusion We show that for expert advice problem, the follow perturbed leading expert algorithm could be equivalent to the modern exponential weighted average algorithm by carefully choosing the perturbation ...
arXiv:1512.07074v1
fatcat:y2jfeefppbdgter3jkuq23wovi
Adaptive Routing Using Expert Advice
2006
Computer journal
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
Machine learning algorithms for combining expert advice in sequential decision problems are considered. ...
The goal of these algorithms is to perform, for any behavior of the system, asymptotically as well as the best expert. ...
ACKNOWLEDGMENT The authors would like to thank László Györfi for useful discussions. ...
doi:10.1093/comjnl/bxh168
fatcat:mnjcaf5abjdsbecsf3stgy75aq
Connections between markets and learning
2010
ACM SIGecom Exchanges
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2016; you can also visit the original URL.
The file type is application/pdf.
We provide an overview of recent research exploring the striking mathematical connections that exist between market maker mechanisms for prediction markets and no-regret learning. ...
We describe how these connections can be used in the design of efficient prediction markets over combinatorial outcome spaces. ...
In general, choosing weights in this manner will prevent all of the algorithm's weight from being placed on a single expert. WM can be written in this form with an entropy term as the regularizer. ...
doi:10.1145/1980534.1980540
fatcat:6miyv5x3f5ewda6nuxtwklrgaa
Efficient algorithms for online decision problems
2005
Journal of computer and system sciences (Print)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2010; you can also visit the original URL.
The file type is application/pdf.
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. ...
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. ...
Acknowledgments We would like to thank Avrim Blum, Bobby Kleinberg, Danny Sleator, and the anonymous referees for their helpful comments. ...
doi:10.1016/j.jcss.2004.10.016
fatcat:rz33fd7qmbc5le6mkslp6l4znq
Efficient Algorithms for Online Decision Problems
[chapter]
2003
Lecture Notes in Computer Science
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2010; you can also visit the original URL.
The file type is application/pdf.
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. ...
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. ...
Acknowledgments We would like to thank Avrim Blum, Bobby Kleinberg, Danny Sleator, and the anonymous referees for their helpful comments. ...
doi:10.1007/978-3-540-45167-9_4
fatcat:hwuni2wxgndylfbpggfzkq5vou
Online Learning in Case of Unbounded Losses Using the Follow Perturbed Leader Algorithm
[article]
2010
arXiv
pre-print
Preserved Fulltext
The Internet Archive has a preservation copy of this work in our general collections.
The file type is application/pdf.
In this paper the sequential prediction problem with expert advice is considered for the case where losses of experts suffered at each step cannot be bounded in advance. ...
We present some modification of Kalai and Vempala algorithm of following the perturbed leader where weights depend on past losses of the experts. ...
To change from the follow leader framework to DTOL we derandomize our FPL algorithm. 2 Games of prediction with expert advice with unbounded one-step losses We consider a game of prediction with expert ...
arXiv:1008.4232v1
fatcat:v3zgiesjtbhmhfjrgo73p3el7i
The Follow Perturbed Leader Algorithm Protected from Unbounded One-Step Losses
[chapter]
2009
Lecture Notes in Computer Science
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
In this paper the sequential prediction problem with expert advice is considered for the case when the losses of experts suffered at each step can be unbounded. ...
We present some modification of Kalai and Vempala algorithm of following the perturbed leader where weights depend on past losses of the experts. ...
Acknowledgments This research was partially supported by Russian foundation for fundamental research: 09-07-00180-a and 09-01-00709a. ...
doi:10.1007/978-3-642-04414-4_8
fatcat:em6pfoeol5cg7k6pqgbb7wkek4
Learning Volatility of Discrete Time Series Using Prediction with Expert Advice
[chapter]
2009
Lecture Notes in Computer Science
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2010; you can also visit the original URL.
The file type is application/pdf.
In this paper the method of prediction with expert advice is applied for learning volatility of discrete time series. ...
For merging different expert strategies in a strategy of the learner, we use some modification of Kalai and Vempala algorithm of following the perturbed leader where weights depend on current gains of ...
Acknowledgments This research was partially supported by Russian foundation for fundamental research: 09-07-00180-a and 09-01-00709-a. ...
doi:10.1007/978-3-642-04944-6_3
fatcat:3fcrmeyzgvelfphbpmms3pvnfm
Adaptive Online Prediction by Following the Perturbed Leader
[article]
2005
arXiv
pre-print
Preserved Fulltext
The Internet Archive has a preservation copy of this work in our general collections.
The file type is application/pdf.
When applying aggregating strategies to Prediction with Expert Advice, the learning rate must be adaptively tuned. ...
The analysis of the alternative "Follow the Perturbed Leader" (FPL) algorithm from Kalai & Vempala (2003) (based on Hannan's algorithm) is easier. ...
The FPL (Follow the Perturbed Leader) approach solves the second problem by adding to each expert's loss s i <t a random perturbation. ...
arXiv:cs/0504078v1
fatcat:vwyj63gmkrecvptbqgwy4cvs3y
Random-Walk Perturbations for Online Combinatorial Optimization
2015
IEEE Transactions on Information Theory
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
RANDOM-WALK PERTURBATIONS FOR PREDICTION WITH EXPERT ADVICE In this section we refine our method to obtain bounds of optimal order in the special case of prediction with expert advice, that is, when the ...
Algorithm 2 Random-walk perturbations for prediction with expert advice. Initialization: set L i,0 = 0 and Z i,0 = 0 for all i = 1, 2, . . . , N . ...
Thus, we are left with the problem of bounding Similarly to [20] , we do this by introducing for all u ∈ S and studying the relationship between the distributions p t andp t . ...
doi:10.1109/tit.2015.2428253
fatcat:p4rcrr6i4beohmqmccjteff4lm
Extracting certainty from uncertainty: regret bounded by variation in costs
2010
Machine Learning
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2016; you can also visit the original URL.
The file type is application/pdf.
Prediction from expert advice is a fundamental problem in machine learning. ...
In this paper we resolve this question, and prove such bounds in the fully adversarial setting, in two important online learning scenarios: prediction from expert advice, and online linear optimization ...
Acknowledgements We thank Martin Zinkevich for initial discussions on the possibility of variation bounds on the regret. ...
doi:10.1007/s10994-010-5175-x
fatcat:ebjmfvg6ovfd3bnnfxdnrzsbfm
Follow the Leader with Dropout Perturbations
2014
Annual Conference Computational Learning Theory
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
We consider online prediction with expert advice. ...
The two most popular algorithms are Hedge/Weighted Majority and Follow the Perturbed Leader (FPL). ...
Acknowledgments Tim van Erven was supported by NWO Rubicon grant 680-50-1112, Wojciech Kotłowski by the Foundation for Polish Science under the Homing Plus Program, and Manfred K. ...
dblp:conf/colt/ErvenK14
fatcat:dsbthrgonzb2zlopm7iidx6ure
Following the Perturbed Leader for Online Structured Learning
2015
International Conference on Machine Learning
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
We investigate a new Follow the Perturbed Leader (FTPL) algorithm for online structured prediction problems. ...
To better understand FTPL algorithms for online structured learning, we present a lower bound on the regret for a large and natural class of FTPL algorithms that use logconcave perturbations. ...
There, the authors have shown a reduction from the problem of shortest path to prediction with expert advice. ...
dblp:conf/icml/CohenH15
fatcat:23gsvqzpmzenbmhmivf6us3yx4
« Previous
Showing results 1 — 15 out of 2,490 results