Filters








17,121 Hits in 7.8 sec

Once bitten, twice shy: experienced regret and non-adaptive choice switching

Francesco Marcatto, Anna Cosulich, Donatella Ferrante
<span title="2015-06-18">2015</span> <i title="PeerJ"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/eyfkjqp7sva5bbnwatk5zazi7q" style="color: black;">PeerJ</a> </i> &nbsp;
The first study presented herein showed that nearly half of participants experiencing regret rejected a previous alternative they had recognized as the best one, and chose a non-optimal alternative instead  ...  Subjects Neuroscience, Psychiatry and Psychology How to cite this article Marcatto et al. (2015) , Once bitten, twice shy: experienced regret and non-adaptive choice switching. PeerJ 3:e1035;  ...  What happens, for example, when people experience regret following an optimal decision, and are faced with the same choice again?  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.7717/peerj.1035">doi:10.7717/peerj.1035</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/26157618">pmid:26157618</a> <a target="_blank" rel="external noopener" href="https://pubmed.ncbi.nlm.nih.gov/PMC4476096/">pmcid:PMC4476096</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/h4ra77jwcnbqpo7zxfzhshezze">fatcat:h4ra77jwcnbqpo7zxfzhshezze</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20171202054031/https://peerj.com/articles/1035.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/81/e7/81e795de2ccc71ece917a1539c673ae706e8a36c.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.7717/peerj.1035"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> Publisher / doi.org </button> </a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4476096" title="pubmed link"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> pubmed.gov </button> </a>

Computing optimal k-regret minimizing sets with top-k depth contours [article]

Sean Chester and Alex Thomo and S. Venkatesh and Sue Whitesides
<span title="2012-07-26">2012</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
To discover an optimal regret minimizing set of a predetermined cardinality is conjectured to be a hard problem.  ...  We design an O(cn^2) plane sweep algorithm for two dimensions to compute an optimal regret minimizing set of cardinality c.  ...  In each cell (i, j) is stored the optimum convex chain from r back to the y-axis which both contains at most j lines and ends on line li.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1207.6329v1">arXiv:1207.6329v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/yqr6pxuobfe4hij4vbktpltzu4">fatcat:yqr6pxuobfe4hij4vbktpltzu4</a> </span>
<a target="_blank" rel="noopener" href="https://archive.org/download/arxiv-1207.6329/1207.6329.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> File Archive [PDF] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1207.6329v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Optimal Control of the Ill-Posed Cauchy Elliptic Problem

A. Berhail, A. Omrane
<span title="">2015</span> <i title="Hindawi Limited"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/4uu6256jlfcsbi67mf5lpcgyo4" style="color: black;">International Journal of Differential Equations</a> </i> &nbsp;
We obtain a singular optimality system characterizing the no-regret control for the Cauchy problem.  ...  From Section 3.1, we showed how to come back from the bi-Laplacian problem to the original one.  ...  We show how to come back to the original Cauchy problem, starting from (10) .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1155/2015/468918">doi:10.1155/2015/468918</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/2sb7ricygjed7ambdkapkajc4e">fatcat:2sb7ricygjed7ambdkapkajc4e</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190429055647/https://hal.univ-guyane.fr/hal-01891254/document" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/18/4e/184ee20e98adeddd7f2a663621c32394fe1c9940.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1155/2015/468918"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> hindawi.com </button> </a>

No more tears: A no-regret approach to power control in dynamically varying MIMO networks

Ioannis Stiakogiannakis, Panayotis Mertikopoulos, Corinne Touati
<span title="">2015</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/qh2yk76dgbetrjgvnslstz3pha" style="color: black;">2015 13th International Symposium on Modeling and Optimization in Mobile, Ad Hoc, and Wireless Networks (WiOpt)</a> </i> &nbsp;
In this dynamic context, we formulate the users' power/throughput trade-off as an online optimization problem and we provide a matrix exponential learning algorithm that leads to no regret -i.e. the proposed  ...  Contrary to the static/stationary channel regime, there is no optimal power allocation profile to converge to (either static or in the mean), so the system's users must adapt to changes in the environment  ...  Instead, we treat power control as a dynamically evolving optimization problem and we employ techniques and ideas from online optimization to quantify how well the system's users adapt to changes in the  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/wiopt.2015.7151107">doi:10.1109/wiopt.2015.7151107</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/wiopt/Stiakogiannakis15.html">dblp:conf/wiopt/Stiakogiannakis15</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ti3m4xselvgdvoscghtigz4r4e">fatcat:ti3m4xselvgdvoscghtigz4r4e</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170811115122/http://dl.ifip.org/db/conf/wiopt/wiopt2015/Stiakogiannakis15.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/ba/a3/baa3056ddc77e3f2ef399624472e6dcf3777e091.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/wiopt.2015.7151107"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Online convex optimization and no-regret learning: Algorithms, guarantees and applications [article]

E. Veronica Belmega, Panayotis Mertikopoulos, Romain Negrel, Luca Sanguinetti
<span title="2018-04-12">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
With this in mind, the aim of this tutorial paper is to provide a gentle introduction to online optimization and learning algorithms that are asymptotically optimal in hindsight - i.e., they approach the  ...  Particular attention is devoted to identifying the algorithms' theoretical performance guarantees and to establish links with classic optimization paradigms (both static and stochastic).  ...  O A G We now turn to the fundamental underlying question arising from the de nition of the regret: How can the optimizer attain a no-regret state, and what is the associated regret minimization rate?  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1804.04529v1">arXiv:1804.04529v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/2vqsvkhjmndyjeetb2tblxskia">fatcat:2vqsvkhjmndyjeetb2tblxskia</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200829023457/https://arxiv.org/pdf/1804.04529v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/de/f0/def04f18d1185683ed6d627014b69a8c1399dcc3.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1804.04529v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Learning the distribution with largest mean: two bandit frameworks [article]

Emilie Kaufmann
<span title="2017-11-07">2017</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
For both of them (regret minimization and best arm identification) we present recent, asymptotically optimal algorithms.  ...  We compare the behaviors of the sampling rule of each algorithm as well as the complexity terms associated to each problem.  ...  dates back to [Agrawal and Goyal, 2012] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1702.00001v3">arXiv:1702.00001v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ua3oi6bd6zhu5fiadonfdhol6i">fatcat:ua3oi6bd6zhu5fiadonfdhol6i</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200826200227/https://arxiv.org/pdf/1702.00001v3.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/31/03/3103832eb692352e1c3ee10520f428d0bf230cdb.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1702.00001v3" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Lifelong Learning in Multi-Armed Bandits [article]

Matthieu Jedor, Jonathan Louëdec, Vianney Perchet
<span title="2020-12-28">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this paper, we study the problem in the multi-armed bandit framework with the objective to minimize the total regret incurred over a series of tasks.  ...  While most bandit algorithms are designed to have a low worst-case regret, we examine here the average regret over bandit instances drawn from some prior distribution which may change over time.  ...  public grant as part of the Investissement d'avenir project, reference ANR-11-LABX-0056-LMH, LabEx LMH, in a joint call with Gaspard Monge Program for optimization, operations research and their interactions  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2012.14264v1">arXiv:2012.14264v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/rycomukpefcurg6ccipuu2esqy">fatcat:rycomukpefcurg6ccipuu2esqy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210106075426/https://arxiv.org/pdf/2012.14264v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/c4/54/c454c1bc809b105994f10d01a623d4a8a401414e.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2012.14264v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Nonstochastic bandits: Countable decision set, unbounded costs and reactive environments

Jan Poland
<span title="">2008</span> <i title="Elsevier BV"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/elaf5sq7lfdxfdejhkqbtz6qoq" style="color: black;">Theoretical Computer Science</a> </i> &nbsp;
We present a variant of our regret minimization algorithm which has still regret of order at most t 1 2 +ε relative to such strong strategies, and even sublinear regret not exceeding O(t 4 5 ) w.r.t. the  ...  A regret minimization algorithm plays this game while achieving sublinear regret relative to each decision.  ...  Gabor Lugosi pointed me at the problem of the [15] analysis with adaptive adversary, and Tom Hayes and Varsha Dani pointed me at the general problem with the "regret in hindsight" notion with adaptive  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.tcs.2008.02.024">doi:10.1016/j.tcs.2008.02.024</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/6bzklixrnbdzjhlpc26sismy74">fatcat:6bzklixrnbdzjhlpc26sismy74</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170924225843/http://publisher-connector.core.ac.uk/resourcesync/data/elsevier/pdf/1da/aHR0cDovL2FwaS5lbHNldmllci5jb20vY29udGVudC9hcnRpY2xlL3BpaS9zMDMwNDM5NzUwODAwMTQzNg%3D%3D.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/25/b2/25b221963705751df02612ee425f27d854951804.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.tcs.2008.02.024"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> elsevier.com </button> </a>

Transitioning nuclear fuel cycles with uncertain fast reactor costs

U.B. Phathanapirom, E.A. Schneider
<span title="">2016</span> <i title="Elsevier BV"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/r4kr7djktzcknc64avxbrwxhma" style="color: black;">Nuclear Engineering and Design</a> </i> &nbsp;
This paper applies a novel decision-making methodology to a case study involving choices leading to the transition from the current once-through light water reactor fuel cycle to one relying on continuous  ...  -Hedging‖ strategies are found by applying a choice criterion to select courses of action which mitigate -regrets‖.  ...  ACKNOLWEDGEMENTS This research is being performed using funding received from the DOE Office of Nuclear Energy's Nuclear Energy University Programs.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.nucengdes.2016.03.011">doi:10.1016/j.nucengdes.2016.03.011</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/psj5kc7ewbhqfktehltih4voyi">fatcat:psj5kc7ewbhqfktehltih4voyi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20180724152728/https://manuscript.elsevier.com/S0029549316001333/pdf/S0029549316001333.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/50/c6/50c618f8452783387ea79dfd1f107c3e4a266d13.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.nucengdes.2016.03.011"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> elsevier.com </button> </a>

Learning the distribution with largest mean: two bandit frameworks

Emilie Kaufmann, Aurélien Garivier, Jean-François Coeurjolly, Adeline Leclercq-Samson
<span title="">2017</span> <i title="EDP Sciences"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/rh6pb37ujvfjbco3fk3nqdq5eu" style="color: black;">ESAIM Proceedings and Surveys</a> </i> &nbsp;
For both of them (regret minimization and best arm identification) we present recent, asymptotically optimal algorithms.  ...  We compare the behaviors of the sampling rule of each algorithm as well as the complexity terms associated to each problem. Résumé.  ...  dates back to [Agrawal and Goyal, 2012] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1051/proc/201760114">doi:10.1051/proc/201760114</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/frh2rxyqf5asfmywaf6xu3rwza">fatcat:frh2rxyqf5asfmywaf6xu3rwza</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20180724034001/https://hal.archives-ouvertes.fr/hal-01449822v3/document" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/0a/0a/0a0af43301fdf473ddafcc661699a93ba9147331.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1051/proc/201760114"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> Publisher / doi.org </button> </a>

Comparison of variant robust SCUC models for operational security and economics of power systems under uncertainty

Bingqian Hu, Lei Wu, Xiaohong Guan, Feng Gao, Qiaozhu Zhai
<span title="">2016</span> <i title="Elsevier BV"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/5zyiklk3jfe4tke3gipnlcy7eq" style="color: black;">Electric power systems research</a> </i> &nbsp;
regret robust model.  ...  Outer approximation (OA) and Benders' decomposition (BD) are used to solve the four robust models.  ...  The OA method is again applied to solve the bilinear optimization problem (9) .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.epsr.2015.11.016">doi:10.1016/j.epsr.2015.11.016</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/i26og6za2zdkrpjvwromk7tis4">fatcat:i26og6za2zdkrpjvwromk7tis4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20180724024042/https://manuscript.elsevier.com/S0378779615003491/pdf/S0378779615003491.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/53/aa/53aa46344eb3d8141360b9e72723860afe7edc7f.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.epsr.2015.11.016"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> elsevier.com </button> </a>

Diversifying with Few Regrets, But too Few to Mention

Zaeem Hussain, Hina A. Khan, Mohamed A. Sharaf
<span title="">2015</span> <i title="ACM Press"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/vxrc3vebzzachiwy3nopwi3h5u" style="color: black;">Proceedings of the Second International Workshop on Databases and the Web - ExploreDB&#39;15</a> </i> &nbsp;
Motivated by that need, in this work we propose a novel scheme called ReDi, which aims to generate representative data that balance the tradeoff between regret minimization and diversity maximization.  ...  Orthogonally, regret minimization has emerged as another technique to generate representative data with high utility that satisfy the user's preference.  ...  minimizing regret and maximizing diversity.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/2795218.2795225">doi:10.1145/2795218.2795225</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/sigmod/HussainKS15.html">dblp:conf/sigmod/HussainKS15</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ugisu5u76ncrpauxjvaagtafcq">fatcat:ugisu5u76ncrpauxjvaagtafcq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190218135209/https://static.aminer.org/pdf/20170130/pdfs/sigmod/9i6tuuk2bdjqc5ontepwjblaf0yrzxew.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/9b/53/9b53c2fe9162ed054d47385a075cb8481b9141ea.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/2795218.2795225"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> acm.org </button> </a>

The α-reliable mean-excess regret model for stochastic facility location modeling

Gang Chen, Mark S. Daskin, Zuo-Jun Max Shen, Stanislav Uryasev
<span title="">2006</span> <i title="Wiley"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/t7lkodpouve6nhkdui2tcdja54" style="color: black;">Naval Research Logistics</a> </i> &nbsp;
We present a new model called the α-reliable meanexcess model that minimizes the expected regret with respect to an endogenously selected subset of worst-case scenarios whose collective probability of  ...  Our mean-excess risk measure is coherent and computationally efficient. Computational experiments also show that the α-reliable mean-excess criterion matches the α-reliable minimax criterion closely.  ...  ACKNOWLEDGMENTS The authors thank Professor John Birge and two anonymous referees for their helpful comments, which led to the improved version.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1002/nav.20180">doi:10.1002/nav.20180</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/hczdpgvmpvfuxbi57xaiv3jf4m">fatcat:hczdpgvmpvfuxbi57xaiv3jf4m</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20100607095107/http://www.ise.ufl.edu/uryasev/Alpha-Reliable_Mean-Excess_Regret_%20Model.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/40/b4/40b40647f24165109f9a31e64985c6307502d2a4.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1002/nav.20180"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> wiley.com </button> </a>

Stochastic Bandits with Vector Losses: Minimizing ℓ^∞-Norm of Relative Losses [article]

Xuedong Shang, Han Shao, Jian Qian
<span title="2020-10-15">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
of cumulative relative losses (which refers to regret minimization).  ...  We define relative loss vector of an arm where the i-th entry compares the arm and the optimal arm with respect to the i-th loss.  ...  The idea is to view the problem again as a minimax game as for regret minimization, which is also a natural observation from the lower bound: given a bandit model ℓ, at each time step a learner plays an  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.08061v1">arXiv:2010.08061v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/hvyhf6slrjaxlo7njgaklkcxq4">fatcat:hvyhf6slrjaxlo7njgaklkcxq4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201021080332/https://arxiv.org/pdf/2010.08061v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/b0/07/b0077754f896e9086c6022240f3afcfb9459aeb1.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.08061v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

MCTS Based on Simple Regret [article]

David Tolpin, Solomon Eyal Shimony
<span title="2012-07-23">2012</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Therefore, it makes more sense to minimize the simple regret, as opposed to the cumulative regret.  ...  We begin by introducing policies for multi-armed bandits with lower finite-time and asymptotic simple regret than UCB, using it to develop a two-stage scheme (SR+CR) for MCTS which outperforms UCT empirically  ...  Research and Production Management.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1207.5536v1">arXiv:1207.5536v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/fckck6zakncnvjvz2sumbc7jzi">fatcat:fckck6zakncnvjvz2sumbc7jzi</a> </span>
<a target="_blank" rel="noopener" href="https://archive.org/download/arxiv-1207.5536/1207.5536.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> File Archive [PDF] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1207.5536v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>
&laquo; Previous Showing results 1 &mdash; 15 out of 17,121 results