Filters








12,259 Hits in 3.7 sec

Discrete Prediction Games with Arbitrary Feedback and Loss (Extended Abstract) [chapter]

Antonio Piccolboni, Christian Schindelhauer
2001 Lecture Notes in Computer Science  
We show that for any discrete loss function and feedback function only one of two situations can occur: either there is a prediction strategy that achieves in Ì rounds a regret of at most Ç´Ì ¿ ´ÐÒ Ì µ  ...  We prove both sides constructively, that is when the loss and feedback functions satisfy a certain condition, we present an algorithm that generates predictions with the claimed performance; otherwise  ...  Gadiel Seroussi, Marcelo Weinberg, Neri Merhav, Nicolò Cesa-Bianchi and Richard Karp provided invaluable feedback about the paper and pointers to the literature.  ... 
doi:10.1007/3-540-44581-1_14 fatcat:5jltob57fbegrlrp2zs3q7suaa

Adaptive Hedging under Delayed Feedback [article]

Alexander Korotin and Vladimir V'yugin and Evgeny Burnaev
2019 arXiv   pre-print
We build the artificial probabilistic framework and use it to prove the adversarial loss bounds for the algorithm G in the delayed feedback setting.  ...  We also show how algorithm G extends classical Hedge (Multiplicative Weights) and adaptive Fixed Share algorithms to the delayed feedback and derive their regret bounds for the delayed setting by using  ...  Prediction with experts' advice can be reduced to Hedging by forgetting about the expert's predictions and using only the computed losses of the experts.  ... 
arXiv:1902.10433v2 fatcat:bbc7s6c2t5dmfkoruzb5cf4yge

Page 349 of Mathematical Reviews Vol. 57, Issue 1 [page]

1979 Mathematical Reviews  
Employing these formulae it is demonstrated that the prediction error method using the determinant of the residual error covariance matrix as loss function is asymptotically efficient with respect to the  ...  In the realization of the Wiener filter with the use of feedback, the transfer matrix G(s) of an open contour is represented by the return-difference matrix F(s)=/+G(s), H(s)=I—(F(s))~*.  ... 

How macroeconomists lost control of stabilization policy: towards dark ages

Jean-Bernard Chatelain, Kirsten Ralf
2020 European Journal of the History of Economic Thought  
This paper is a study of the history of the transplant of mathematical tools using negative feedback for macroeconomic stabilization policy from 1948 to 1975 and the subsequent break of the use of control  ...  The Lucas critique and Kydland and Prescott's time-inconsistency were over-statements that led to the "dark ages" of the prevalence of the stabilization-policy-ineffectiveness idea.  ...  to an optimal rule λ * R Q , with identical predictions and behavior of the policy maker.  ... 
doi:10.1080/09672567.2020.1817119 fatcat:qilx6ndkxvhfbpqgbicc2tyosm

2018 Index IEEE Transactions on Automatic Control Vol. 63

2018 IEEE Transactions on Automatic Control  
., +, TAC Jan. 2018 174-188 Robust Exponential Stability and Disturbance Attenuation for Discrete-Time Switched Systems Under Arbitrary Switching.  ...  Li, Y., +, TAC April 2018 973-988 Robust Exponential Stability and Disturbance Attenuation for Discrete-Time Switched Systems Under Arbitrary Switching.  ... 
doi:10.1109/tac.2019.2896796 fatcat:bwmqasulnzbwhin5hv4547ypfe

A Combined Multiple Model Adaptive Control Scheme and Its Application to Nonlinear Systems With Nonlinear Parameterization

Weitian Chen, Brian D. O. Anderson
2012 IEEE Transactions on Automatic Control  
., and Chen, T., Sampled-Data Consensus for Multiple Double Integrators With Arbitrary Sampling; TAC Dec. 2012 3230-3235 Xiao, N., Xie, L., and Qiu, L., Feedback Stabilization of Discrete-Time Networked  ...  ., +, TAC April 2012 973-988 The Explicit Constrained Min-Max Model Predictive Control of a Discrete-Time Linear System With Uncertain Disturbances.  ... 
doi:10.1109/tac.2011.2176162 fatcat:2airdooti5fi7kmuozmodywcga

Software for continuous game experiments

James Pettit, Daniel Friedman, Curtis Kephart, Ryan Oprea
2014 Experimental Economics  
It allows experimenters with limited programming experience to create a variety of strategic environments featuring rich visual feedback in continuous time and over continuous action spaces, as well as  ...  ConG is software for conducting economic experiments in continuous and discrete time.  ...  User interface for a simultaneous-move discrete-time game with ConG software.  ... 
doi:10.1007/s10683-013-9387-3 fatcat:favo4cbqpncx7pxquvso6h2vlm

Characterizing the dynamics of learning in repeated reference games [article]

Robert D. Hawkins, Michael C. Frank, Noah D. Goodman
2020 arXiv   pre-print
Finally, we find systematic structure in how a speaker's referring expressions become more efficient over time: syntactic units drop out in clusters following positive feedback from the listener, eventually  ...  We release an open corpus (>15,000 utterances) of extended dyadic interactions in a classic repeated reference game task where pairs of participants had to coordinate on how to refer to initially difficult-to-describe  ...  We predicted that the matcher's use of backchannel feedback should be highest on the first repetition and drop off once meanings are agreed upon, consistent with the patterns observed by (Clark & Wilkes-Gibbs  ... 
arXiv:1912.07199v2 fatcat:4nl6aymhnrb4hcd35atda574ru

2015 Index IEEE Transactions on Automatic Control Vol. 60

2015 IEEE Transactions on Automatic Control  
., +, TAC Aug. 2015 2195-2200 Distributed Reactive Power Feedback Control for Voltage Regulation and Loss Minimization.  ...  Kenne, G., +, TAC Sept. 2015 2464-2469 Distributed Reactive Power Feedback Control for Voltage Regulation and Loss Minimization.  ... 
doi:10.1109/tac.2015.2512305 fatcat:5gut6qeomfh73fwfvehzujbr5q

Characterizing the Dynamics of Learning in Repeated Reference Games

Robert D. Hawkins, Michael C. Frank, Noah D. Goodman
2020 Cognitive Science  
Finally, we find systematic structure in how a speaker's referring expressions become more efficient over time: Syntactic units drop out in clusters following positive feedback from the listener, eventually  ...  We release an open corpus (>15,000 utterances) of extended dyadic interactions in a classic repeated reference game task where pairs of participants had to coordinate on how to refer to initially difficult-to-describe  ...  We predicted that the matcher's use of backchannel feedback should be highest on the first repetition and drop off once meanings are agreed upon, consistent with the patterns observed by Clark and Wilkes-Gibbs  ... 
doi:10.1111/cogs.12845 pmid:32496603 fatcat:sabib2pmqrhffojnftglpsautu

Learning to Draw: Emergent Communication through Sketching [article]

Daniela Mihai, Jonathon Hare
2021 arXiv   pre-print
Existing research has focused on language, with a learned communication channel transmitting sequences of discrete tokens between the agents.  ...  In the framework of a referential communication game, we demonstrate that agents can not only successfully learn to communicate by drawing, but with appropriate inductive biases, can do so in a fashion  ...  Acknowledgments and Disclosure of Funding D.M. is supported by the EPSRC Doctoral Training Partnership (EP/R513325/1).  ... 
arXiv:2106.02067v2 fatcat:dkje23cld5bydcldiewypuxuj4

2019 Index IEEE Transactions on Control of Network Systems Vol. 6

2019 IEEE Transactions on Control of Network Systems  
., +, TCNS June 2019 586-597 Feedback An Event-Triggered Output-Based Model Predictive Control Strategy.  ...  Col, L.D., +, TCNS June 2019 789-799 B Bayes methods Bayesian Filtering With Unknown Sensor Measurement Losses.  ... 
doi:10.1109/tcns.2020.2967203 fatcat:y7saxrrnzvgxjmzz2vrl62ranu

Open-loop and feedback models of dynamic oligopoly

Larry S. Karp, Jeffrey M. Perloff
1993 International Journal of Industrial Organization  
Agent i's loss from a failure to respond to a change in u. 3 I 1 consists of two components: the reduction of his profits in the current period and the present value of the loss of finding himself with  ...  Finally, a summary and conclusions are presented. 1. Definitions and the Model lye start with a discrete time model in which the length of a period is E. !  ...  We show that This inequality, together with (AI.lb) and (A1.1~) and (A1.2b) and (AI.Zc), and the definition of 9 ' and pf establish Proposition 2. We first establish that F,,(?  ... 
doi:10.1016/0167-7187(93)90015-5 fatcat:tiuecgyg5fc2zonkexx5tvshs4

Towards the PAC Learnability of Nash Equilibrium [article]

Zhijian Duan, Dinghuai Zhang, Wenhan Huang, Yali Du, Jun Wang, Yaodong Yang, Xiaotie Deng
2022 arXiv   pre-print
Nash equilibrium (NE) is one of the most important solution concepts in game theory and has broad applications in machine learning research.  ...  Our results justify the feasibility of approximating NE through purely data-driven approaches, which benefits both game theorists and machine learning practitioners.  ...  Notice that we consider games with a fixed number of players and actions so that for arbitrary two games in U they only differ in their game utilities.  ... 
arXiv:2108.07472v4 fatcat:hp374n4fvjcpfow5ebhqzbkoja

2020 Index IEEE Transactions on Automatic Control Vol. 65

2020 IEEE Transactions on Automatic Control  
., +, TAC Aug. 2020 3241-3255 Codesign of Event Trigger and Feedback Policy in Robust Model Predictive Control.  ...  Li, F., +, TAC May 2020 2163-2170 Codesign of Event Trigger and Feedback Policy in Robust Model Predictive Control.  ...  Linear programming A Decentralized Event-Based Approach for Robust Model Predictive Control.  ... 
doi:10.1109/tac.2020.3046985 fatcat:hfiqhyr7sffqtewdmcwzsrugva
« Previous Showing results 1 — 15 out of 12,259 results