Filters








6,060 Hits in 3.3 sec

Stochastic Online Learning with Probabilistic Graph Feedback [article]

Shuai Li, Wei Chen, Zheng Wen, Kwong-Sak Leung
2019 arXiv   pre-print
We consider a problem of stochastic online learning with general probabilistic graph feedback, where each directed edge in the feedback graph has probability p_ij. Two cases are covered.  ...  (b) The cascade case where after playing arm i the learner observes feedback of all arms j in a probabilistic cascade starting from i– for each (i,j) with probability p_ij, if arm i is played or observed  ...  Conclusion and Future Work We are the first to formalize the setting of stochastic online learning with probabilistic feedback graph.  ... 
arXiv:1903.01083v2 fatcat:w2lxoy527fdcpokwufynqa2p7q

Stochastic Online Learning with Probabilistic Graph Feedback

Shuai Li, Wei Chen, Zheng Wen, Kwong-Sak Leung
2020 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
We consider a problem of stochastic online learning with general probabilistic graph feedback, where each directed edge in the feedback graph has probability pij. Two cases are covered.  ...  (b) The cascade case where after playing arm i the learner observes feedback of all arms j in a probabilistic cascade starting from i – for each (i,j) with probability pij, if arm i is played or observed  ...  Conclusion and Future Work We are the first to formalize the setting of stochastic online learning with probabilistic feedback graph.  ... 
doi:10.1609/aaai.v34i04.5899 fatcat:kmmfsmdkcbethilgobo26ctb2m

Online Learning with Feedback Graphs Without the Graphs [article]

Alon Cohen, Tamir Hazan, Tomer Koren
2016 arXiv   pre-print
We study an online learning framework introduced by Mannor and Shamir (2011) in which the feedback is specified by a graph, in a setting where the graph may vary from round to round and is never fully  ...  In contrast, in the stochastic case we give an algorithm that achieves Θ(√(α T)) regret over T rounds, provided that the independence numbers of the hidden feedback graphs are at most α.  ...  Nevertheless, in the case of stochastic losses, our positive results do extend to the more general feedback model. 1.2 Additional related work Online learning with feedback graphs was previously  ... 
arXiv:1605.07018v1 fatcat:uivua4t5rrhxdbulm3etzm5uha

Learning Stochastic Parametric Differentiable Predictive Control Policies [article]

Ján Drgoňa, Sayak Mukherjee, Aaron Tuor, Mahantesh Halappanavar, Draguna Vrabie
2022 arXiv   pre-print
We provide theoretical probabilistic guarantees for policies learned via the SP-DPC method on closed-loop stability and chance constraints satisfaction.  ...  To address this challenge, we present a scalable alternative called stochastic parametric differentiable predictive control (SP-DPC) for unsupervised learning of neural control policies governing stochastic  ...  In particular, we combine the classical ideas of deterministic sampling of chance-constrained together with feedback parametrization from stochastic MPC literature with recent ideas from learning-based  ... 
arXiv:2203.01447v1 fatcat:vmsg2tcwgzb3nc2iqncmu4upeu

2020 Index IEEE Transactions on Neural Networks and Learning Systems Vol. 31

2020 IEEE Transactions on Neural Networks and Learning Systems  
Adaptive Graph Learning; TNNLS May 2020 1592-1601 Zhou, R., Guo, Y., Wu, Y., and Gui, W., Asymptotical Feedback Set Stabilization of Probabilistic Boolean Control Networks; TNNLS Nov. 2020 4524-4537 Zhou  ...  Gener-ming Algorithm for Online Learning.  ... 
doi:10.1109/tnnls.2020.3045307 fatcat:34qoykdtarewhdscxqj5jvovqy

2020 Index IEEE Transactions on Cybernetics Vol. 50

2020 IEEE Transactions on Cybernetics  
., +, TCYB June 2020 2346-2356 Learning Graph Embedding With Adversarial Training Methods.  ...  ., +, TCYB May 2020 1833-1843 Robust Online Multilabel Learning Under Dynamic Changes in Data Distribution With Labels.  ...  Stock markets A Quantum-Inspired Similarity Measure for the Analysis of Complete Weighted Graphs. Bai, L., +, TCYB March 2020 1264 -1277  ... 
doi:10.1109/tcyb.2020.3047216 fatcat:5giw32c2u5h23fu4drupnh644a

Table of contents

2020 IEEE Transactions on Neural Networks and Learning Systems  
Mu 4512 Asymptotical Feedback Set Stabilization of Probabilistic Boolean Control Networks ...................................... ........................................................................  ...  Braga 4761 A Stochastic Quasi-Newton Method for Large-Scale Nonconvex Optimization With Applications ....................... ............................................................................  ... 
doi:10.1109/tnnls.2020.3030506 fatcat:fnp55kp7orandbtqp3oebxuj6i

Online Learning with Uncertain Feedback Graphs [article]

Pouya M Ghari, Yanning Shen
2021 arXiv   pre-print
feedback graph.  ...  Online learning with expert advice is widely used in various machine learning tasks. It considers the problem where a learner chooses one from a set of experts to take advice and make a decision.  ...  G t ; and ii) online learning with uninformative probabilistic feedback graph: where only the nominal feedback graph G t is revealed, but not the probabilities.  ... 
arXiv:2106.08441v1 fatcat:qrcpsslppnffnmgcy5vw4f3nsa

Reinforcement Learning based Stochastic Shortest Path Finding in Wireless Sensor Networks

Wenwen Xia, Chong Di, Haonan Guo, Shenghong Li
2019 IEEE Access  
This dynamic property makes the network essentially form a graph with stochastic edge lengths.  ...  In this paper, we study the stochastic shortest path problem on a directional graph with stochastic edge lengths, using reinforcement learning algorithms. we regard each edge length as a random variable  ...  The proposed algorithms learn and find the stochastic shortest path in an online manner, utilizing every timestep's feedback to adjust state-action value functions, instead of the whole path's feedback  ... 
doi:10.1109/access.2019.2950055 fatcat:4lsmounvafcdhldfzxsexxs5ri

Robot learning with a spatial, temporal, and causal and-or graph

Caiming Xiong, Nishant Shukla, Wenlong Xiong, Song-Chun Zhu
2016 2016 IEEE International Conference on Robotics and Automation (ICRA)  
We propose a stochastic graph-based framework for a robot to understand tasks from human demonstrations and perform them with feedback control.  ...  The learning system can watch human demonstrations, generalize learned concepts, and perform tasks in new environments, across different robotic platforms.  ...  An Or-node is a probabilistic switch deciding which of the sub-graphs to accept. It is denoted by an open circle with out-going edges drawn in dashed lines.  ... 
doi:10.1109/icra.2016.7487364 dblp:conf/icra/XiongSXZ16 fatcat:agdxx2bwbvcf5l43dkldvmt42m

Table of contents

2021 IEEE Transactions on Cybernetics  
Tan 3143 Deep-Learning-Based Probabilistic Forecasting of Electric Vehicle Charging Load With a Novel Queuing Model . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .  ...  Sun 3263 Consensus Affinity Graph Learning for Multiple Kernel Clustering . . . . . . . . . . . . . . . . . . . Z. Ren, S. X. Yang, Q. Sun, and T.  ... 
doi:10.1109/tcyb.2021.3078403 fatcat:khtr32736jbo5ftobscdamapba

2014 Index IEEE Transactions on Neural Networks and Learning Systems Vol. 25

2014 IEEE Transactions on Neural Networks and Learning Systems  
., +, TNNLS Mar. 2014 557-570 Online Bayesian Learning With Natural Sequential Prior Distribution.  ...  P., +, TNNLS Jan. 2014 241-246 MLMVN With Soft Margins Learning. Aizenberg, I., TNNLS Sep. 2014 1632-1644 Online Bayesian Learning With Natural Sequential Prior Distribution.  ... 
doi:10.1109/tnnls.2015.2396731 fatcat:ztnfcozrejhhfdwg7t2f5xlype

Probabilistic Methods in the Design and Analysis of Algorithms (Dagstuhl Seminar 17141)

Bodo Manthey, Claire Mathieu, Heiko Röglin, Eli Upfal, Marc Herbstritt
2017 Dagstuhl Reports  
The seminar was on probabilistic methods with a focus on the design and analysis of algorithms.  ...  Probabilistic methods play a central role in theoretical computer science.  ...  We derive the first performance guarantees for an online algorithm that schedules stochastic, nonpreemptive jobs on unrelated machines to minimize the expectation of the total weighted completion time.  ... 
doi:10.4230/dagrep.7.4.1 dblp:journals/dagstuhl-reports/MantheyMRU17 fatcat:37g24odqhvg3rnlpudblwug6hy

An Introduction to Probabilistic Spiking Neural Networks: Probabilistic Models, Learning Rules, and Applications [article]

Hyeryung Jang, Osvaldo Simeone, Brian Gardner, André Grüning
2019 arXiv   pre-print
We adopt discrete-time probabilistic models for networked spiking neurons and derive supervised and unsupervised learning rules from first principles via variational inference.  ...  This article provides an introduction to SNNs by focusing on a probabilistic signal processing methodology that enables the direct derivation of learning rules by leveraging the unique time-encoding capabilities  ...  To this end, consider an ANN with an arbitrary topology defined by an acyclic directed graph.  ... 
arXiv:1910.01059v2 fatcat:2apx42l5rndthj2azsclqz5b2m

Scanning the Issue*

2017 IEEE Transactions on Automatic Control  
The performance of the algorithm is tested on low-complexity robust matrix completion and sparse learning. This paper deals with distributed learning in a network of agents.  ...  An improved learning protocol with better scalability with respect to the number of nodes in the network is discussed in the case of a static network.  ...  Nedich This paper deals with distributed learning in a network of agents.  ... 
doi:10.1109/tac.2017.2758058 fatcat:menj6pkrtbh45gyglgh3qrgspy
« Previous Showing results 1 — 15 out of 6,060 results