Filters








4,549 Hits in 7.6 sec

Online Algorithm for Unsupervised Sequential Selection with Contextual Information [article]

Arun Verma, Manjesh K. Hanawal, Csaba Szepesvári, Venkatesh Saligrama
2020 arXiv   pre-print
In this paper, we study Contextual Unsupervised Sequential Selection (USS), a new variant of the stochastic contextual bandits problem where the loss of an arm cannot be inferred from the observed feedback  ...  Under CWD, we propose an algorithm for the contextual USS problem and demonstrate that it has sub-linear regret. Experiments on synthetic and real datasets validate our algorithm.  ...  Dua Supplementary Material: 'Online Algorithm for Unsupervised Sequential Selection with Contextual Information' A Missing proofs from Section 2 A.1 Proof of Lemma 1 Lemma 1.  ... 
arXiv:2010.12353v1 fatcat:drhvr7sw7vaffafuixyo2nj2zu

Contextual Bandit with Missing Rewards [article]

Djallel Bouneffouf, Sohini Upadhyay, Yasaman Khazaeni
2020 arXiv   pre-print
We consider a novel variant of the contextual bandit problem (i.e., the multi-armed bandit with side-information, or context, available to a decision-maker) where the reward associated with each context-based  ...  In order to address the missing rewards setting, we propose to combine the standard contextual bandit approach with an unsupervised learning mechanism such as clustering.  ...  More specifically, we will combine unsupervised online clustering with the standard contextual bandit.  ... 
arXiv:2007.06368v2 fatcat:azyowuenyve6bhxhfj75knj2my

Diverse Sequential Subset Selection for Supervised Video Summarization

Boqing Gong, Wei-Lun Chao, Kristen Grauman, Fei Sha
2014 Neural Information Processing Systems  
To this end, we propose the sequential determinantal point process (seqDPP), a probabilistic model for diverse sequential subset selection.  ...  Our idea is to teach the system to learn from human-created summaries how to select informative and diverse subsets, so as to best meet evaluation metrics derived from human-perceived quality.  ...  We are grateful to Jiebo Luo for providing the Kodak dataset [32] .  ... 
dblp:conf/nips/GongCGS14 fatcat:q2sjg3ugu5f2ta2bjx4ldywuu4

A Survey on Practical Applications of Multi-Armed and Contextual Bandits [article]

Djallel Bouneffouf, Irina Rish
2019 arXiv   pre-print
performance combined with certain attractive properties, such as learning from less feedback.  ...  Specifically, we introduce a taxonomy of common MAB-based applications and summarize state-of-art for each of those domains.  ...  They propose a contextual multi-armed bandit model with a nonlinear reward function that uses distributed representation of text for online response selection.  ... 
arXiv:1904.10040v1 fatcat:j6v37wy7f5bmvpfzzhtnutbeoa

CARS: Workshop on Context-Aware Recommender Systems 2022

Gediminas Adomavicius, Konstantin Bauman, Bamshad Mobasher, Francesco Ricci, Alexander Tuzhilin, Moshe Unger
2022 Sixteenth ACM Conference on Recommender Systems  
information and cope with their dynamic properties in group recommendations and in online environments.  ...  Contextual information has been widely recognized as an important modeling dimension in social sciences and in computing.  ...  For example, latent context-aware recommender systems [24, 26] utilize unsupervised learning techniques for modeling implicit contextual information derived from mobile devices.  ... 
doi:10.1145/3523227.3547421 fatcat:irc7djlndndyra24fxdwckdhri

Online Semi-Supervised Learning in Contextual Bandits with Episodic Reward [article]

Baihan Lin
2020 arXiv   pre-print
We considered a novel practical problem of online learning with episodically revealed rewards, motivated by several real-world applications, where the contexts are nonstationary over different episodes  ...  side information when rewards are not observed.  ...  For Warfarin dataset, we selected the first 5,000 training samples to simulate the online bandit with 3 arms (classes).  ... 
arXiv:2009.08457v2 fatcat:vhvcravl2fg7dmyjoptfwsrnmu

Sequential Detection of Microgrid Bad Data via a Data-Driven Approach Combining Online Machine Learning With Statistical Analysis

Heming Huang, Fei Liu, Tinghui Ouyang, Xiaoming Zha
2022 Frontiers in Energy Research  
In this paper, the authors propose a sequential detection method that combines three data mining algorithms, that is the Online Sequential Extreme Learning Machine (OSELM), statistical analysis within  ...  After sequential data training, OSELM is used to construct an online updated error-filtering map to extract the electrical feature of the microgrid data sequence.  ...  ACKNOWLEDGMENTS The authors would like to thank Professor Andrew Kusiak at the University of Iowa for his academic support on this paper.  ... 
doi:10.3389/fenrg.2022.861563 fatcat:ec4npvjy3jgbnk5bxzfa3qczc4

Interaction-Grounded Learning [article]

Tengyang Xie, John Langford, Paul Mineiro, Ida Momennejad
2021 arXiv   pre-print
We propose Interaction-Grounded Learning for this novel setting, in which a learner's goal is to interact with the environment with no grounding or explicit reward to optimize its policies.  ...  In order to succeed, the algorithm must learn how to evaluate the feedback vector to discover a latent reward signal, with which it can ground its policies without supervision.  ...  Online algorithm for unsupervised sequential selection with contextual information. arXiv preprint arXiv:2010.12353, 2020. Zhou, L. and Brunskill, E.  ... 
arXiv:2106.04887v2 fatcat:h6lwbjlq3jcxnaqfx54h7luks4

Online Learning: A Comprehensive Survey [article]

Steven C.H. Hoi, Doyen Sahoo, Jing Lu, Peilin Zhao
2018 arXiv   pre-print
where full feedback information is always available, (ii) online learning with limited feedback, and (iii) unsupervised online learning where there is no feedback available.  ...  Online learning represents an important family of machine learning algorithms, in which a learner attempts to resolve an online prediction (or any type of decision-making) task by learning a model/hypothesis  ...  Unsupervised learning tasks: Online learning algorithms can be applied for unsupervised learning tasks.  ... 
arXiv:1802.02871v2 fatcat:mqorsb4gknhfhjfb4jcsvbrtwm

Unsupervised Feature Selection for Outlier Detection on Streaming Data to Enhance Network Security

Michael Heigl, Enrico Weigelt, Dalibor Fiala, Martin Schramm
2021 Applied Sciences  
Thus, a novel algorithm for Unsupervised Feature Selection for Streaming Outlier Detection, denoted as UFSSOD, will be proposed, which is able to perform unsupervised feature selection for the purpose  ...  A generic concept that shows two application scenarios of UFSSOD in conjunction with off-the-shell online outlier detection algorithms has been derived.  ...  Informed Consent Statement: Not applicable.  ... 
doi:10.3390/app112412073 fatcat:afwczjw7f5dihcarbx7k73cbsm

Machine Learning for Anomaly Detection: A Systematic Review

Ali Bou Nassif, Manar Abu Talib, Qassim Nasir, Fatima Mohamad Dakalbab
2021 IEEE Access  
"Informed consent: This study does not involve any experiments on animals or humans".  ...  We are also grateful to our research assistants who helped in collecting, summarizing, and analyzing the research articles for this SLR study.  ...  Videos" Conf. [110] A83 "Anomaly Detection by Using CFS Subset and Neural Network with WEKA Tools" Conf. [111] A84 "Online Learning and Sequential Anomaly Detection in Trajectories" Jour. 2013 [112  ... 
doi:10.1109/access.2021.3083060 fatcat:vv7qthbvqjdz7ksm3yosulk22q

Identifying machine learning techniques for classification of target advertising

Jin-A Choi, Kiho Lim
2020 ICT Express  
The paper also identifies an underexamined area, algorithm-based detection of click frauds, to illustrate how machine learning approaches can be integrated to preserve the viability of online advertising  ...  This study investigates and classifies various machine learning techniques that are used to enhance targeted online advertising.  ...  The proposed framework uses Maximum Entropy (also known as logistic regression) with a two-phase feature selection algorithm (feature selection and value selection) for increasing automation and reducing  ... 
doi:10.1016/j.icte.2020.04.012 fatcat:5qnbssw625chhfeeqkwzkgcjxm

CMIB: Unsupervised Image Object Categorization in Multiple Visual Contexts

Xiaoqiang Yan, Yangdong Ye, Xueying Qiu, Milos Manic, Hui Yu
2019 IEEE Transactions on Industrial Informatics  
In this work, we propose a novel contextual multivariate information bottleneck (CMIB) method to conduct unsupervised image object categorization in multiple visual contexts.  ...  ., scale-invariant feature transform, SIFT) as content information of the objects, while regarding image tags as their contextual information.  ...  NUS-22 5 consists of online images and the associated tags, with a total number of 81 unique categories. We select 22 categories with a total number of 10500 images in our experiment. B.  ... 
doi:10.1109/tii.2019.2939278 fatcat:zwnrhv64cnhh7eyvqbvwhplsxu

Ensemble Consensus: An Unsupervised Algorithm for Anomaly Detection in Network Security data

Vincenzo Dentamaro, Vito Nicola Convertini, Stefano Galantucci, Paolo Giglio, Tonino Palmisano, Giuseppe Pirlo
2021 Italian Conference on Cybersecurity  
In this work the Anomaly Consensus algorithm for unsupervised network analysis is presented.  ...  The algorithm aim is to fuse the three most important anomaly detection techniques for unsupervised detection of suspicious events.  ...  of the unsupervised Anomaly Consensus algorithm (in bold) with supervised learning algorithms  ... 
dblp:conf/itasec/DentamaroCGGPP21 fatcat:srrv4pahbvajni6wfa7b3lyzhq

Learning Probabilistic Models of Word Sense Disambiguation [article]

Ted Pedersen
2007 arXiv   pre-print
The supervised methods focus on performing model searches through a space of probabilistic models, and the unsupervised methods rely on the use of Gibbs Sampling and the Expectation Maximization (EM) algorithm  ...  An explanation for this success is presented in terms of learning rates and bias-variance decompositions.  ...  The information criteria have a number of appealing properties that make them particularly well suited for sequential model selection.  ... 
arXiv:0707.3972v1 fatcat:c452544gqrgxvk7sb7toetv3si
« Previous Showing results 1 — 15 out of 4,549 results