139 Hits in 4.5 sec

Near-optimal Batch Mode Active Learning and Adaptive Submodular Optimization

Yuxin Chen, Andreas Krause
2013 International Conference on Machine Learning  
We consider batch mode active learning and more general information-parallel stochastic optimization problems that exhibit adaptive submodularity, a natural diminishing returns condition.  ...  While several heuristics have been proposed for batch-mode active learning, little is known about their theoretical performance.  ...  This research was supported in part by SNSF grant 200021 137971, NSF IIS-0953413, DARPA MSEE FA8650-11-1-7156 and ERC StG 307036.  ... 
dblp:conf/icml/ChenK13 fatcat:lfaklg6gpnfdfe3fx53vyanz4i

Adaptive Submodularity with Varying Query Sets: An Application to Active Multi-label Learning

Alan Fern, Robby Goetschalckx, Mandana Hamidi-Haines, Prasad Tadepalli
2017 International Conference on Algorithmic Learning Theory  
Adaptive submodular optimization, where a sequence of items is selected adaptively to optimize a submodular function, has been found to have many applications from sensor placement to active learning.  ...  A natural application of this framework is to crowd-sourced active learning problem where the set of available experts and examples might vary randomly.  ...  N00014-11-1-0106), and DARPA (grant no. DARPA N66001-17-2-4030).  ... 
dblp:conf/alt/FernGHT17 fatcat:jgfwcotc5raopegls6lzqf37xa

Active Learning for Probabilistic Hypotheses Using the Maximum Gibbs Error Criterion

Viet Cuong Nguyen, Wee Sun Lee, Nan Ye, Kian Ming Adam Chai, Hai Leong Chieu
2013 Neural Information Processing Systems  
We apply this maximum Gibbs error criterion to three active learning scenarios: non-adaptive, adaptive, and batch active learning.  ...  This objective function, called the policy Gibbs error, is the expected error rate of a random classifier drawn from the prior distribution on the examples adaptively selected by the active learning policy  ...  Acknowledgments This work is supported by DSO grant DSOL11102 and the US Air Force Research Laboratory under agreement number FA2386-12-1-4031.  ... 
dblp:conf/nips/NguyenLYCC13 fatcat:5viidvokpvdxlgqhjmd6ftlge4

Active Learning Methods based on Statistical Leverage Scores [article]

Cem Orhan, Oznur Tastan
2018 arXiv   pre-print
The submodularity property of the set scoring function let us identify batches with a constant factor approximate to the optimal batch in an efficient manner.  ...  and DBALEVS for querying a batch of examples.  ...  -Near-optimal batch mode active learning (NearOpt) : NearOpt [5] Fig. 4 : 4 Comparison of DBALEVS with other methods on classification accuracy. the batch size is large enough, the examples provide valuable  ... 
arXiv:1812.02497v1 fatcat:nq2pvicopjbcfm2fv2bcfvvslu

Batch Active Preference-Based Learning of Reward Functions [article]

Erdem Bıyık, Dorsa Sadigh
2018 arXiv   pre-print
We introduce several approximations to the batch active learning problem, and provide theoretical guarantees for the convergence of our algorithms.  ...  Our results suggest that our batch active learning algorithm requires only a few queries that are computed in a short amount of time.  ...  Near-optimal batch mode active learning and adaptive submodular optimization. ICML (1), 28:160–168, 2013. [6] D. Sadigh, A. D. Dragan, S. S. Sastry, and S. A. Seshia.  ... 
arXiv:1810.04303v1 fatcat:polkkouvsrhgnjqewkaxqjyghu

Active Learning: Problem Settings and Recent Developments [article]

Hideitsu Hino
2020 arXiv   pre-print
This paper explains the basic problem settings of active learning and recent research trends.  ...  Active learning is a method of obtaining predictive models with high precision at a limited cost through the adaptive selection of samples for labeling.  ...  Acknowledgement The author is supported by JST JPMJCR1761 and JPMJMI19G1. The author thank Dr. Hideaki Ishibashi, Tetsuro Ueno, Kanta Ono and Mr.  ... 
arXiv:2012.04225v2 fatcat:rbtg2kvi6vhj3odzayph4floum

Learning and Optimization with Submodular Functions [article]

Bharath Sankaran, Marjan Ghazvininejad, Xinran He, David Kale, Liron Cohen
2015 arXiv   pre-print
In this paper we will review the formal definition of submodularity; the optimization of submodular functions, both maximization and minimization; and finally discuss some applications in relation to learning  ...  In this report we will study design and optimization over a common class of functions called submodular functions.  ...  algorithm that queries labels in batches of size k > 1 and show that this approach is competitive not only with optimal batch-more active learning but also with more traditional greedy active learning  ... 
arXiv:1505.01576v1 fatcat:sruylmithjdnddnliq5mylq7ry

Learning From Less Data: A Unified Data Subset Selection and Active Learning Framework for Computer Vision [article]

Vishal Kaushal, Rishabh Iyer, Suraj Kothawade, Rohan Mahadev, Khoshrav Doctor, Ganesh Ramakrishnan
2019 arXiv   pre-print
Training data subset selection and active learning techniques have been proposed as possible solutions to these challenges.  ...  They can also help improve the efficiency of active learning in further reducing human labeling efforts by selecting a subset of the examples obtained using the conventional uncertainty sampling based  ...  The authors would like to thank Suyash Shetty, Anurag Sahoo, Narsimha Raju and Pankaj Singh for discussions and useful suggestions on the manuscripts.  ... 
arXiv:1901.01151v1 fatcat:qynsco4vcrhx3atvengh2qz2sa

Randomised Gaussian Process Upper Confidence Bound for Bayesian Optimisation

Julian Berk, Sunil Gupta, Santu Rana, Svetha Venkatesh
2020 Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence  
We also provide results showing that our method achieves better performance than GP-UCB in a range of real-world and synthetic problems.  ...  ., 1997] , gives a near-optimal solution.  ...  ., 2015] select a batch of diverse and informative samples by posing active learning as a submodular subset selection problem.  ... 
doi:10.24963/ijcai.2020/312 dblp:conf/ijcai/KumariGCC20 fatcat:t6l6srkcufe5bihmudcgs4fazu

Adaptive Sequence Submodularity [article]

Marko Mitrovic and Ehsan Kazemi and Moran Feldman and Andreas Krause and Amin Karbasi
2019 arXiv   pre-print
In this paper, we view the problem of adaptive and sequential decision making through the lens of submodularity and propose an adaptive greedy policy with strong theoretical guarantees.  ...  Without further structure, finding an optimal sequence is notoriously challenging, if not completely intractable.  ...  Submodular maximization meets streaming: Matchings, matroids, and more. IPCO, 2014. Yuxin Chen and Andreas Krause. Near-optimal batch mode active learning and adaptive submodular optimization.  ... 
arXiv:1902.05981v2 fatcat:ilme35kt4bapznevpthydyz6zm

Data-driven robotic sampling for marine ecosystem monitoring

Jnaneshwar Das, Frédéric Py, Julio B.J. Harvey, John P. Ryan, Alyssa Gellene, Rishi Graham, David A. Caron, Kanna Rajan, Gaurav S. Sukhatme
2015 The international journal of robotics research  
In this paper, we present a data-driven and opportunistic sampling strategy to minimize cumulative regret for batches of plankton samples acquired by an AUV over multiple surveys.  ...  In addition to extensive simulations using historical field data, we present results from a one-day field trial where beginning with a prior model learned from data collected and labeled in an earlier  ...  Acknowledgements We thank the David and Lucile Packard Foundation for supporting our work at Monterey Bay Aquarium Research Institute, and the crew of the R/V Zephyr and R/V Rachel Carson for help with  ... 
doi:10.1177/0278364915587723 fatcat:jv6albuvobh2tm2rzlrxjyftna

Budgeted Nonparametric Learning from Data Streams

Ryan Gomes, Andreas Krause
2010 International Conference on Machine Learning  
We develop an efficient algorithm, Stream-Greedy, which is guaranteed to obtain a constant fraction of the value achieved by the optimal solution to this NP-hard optimization problem.  ...  Examples of this problem include exemplarbased clustering and nonparametric inference such as Gaussian process regression on massive data sets.  ...  This research was partially supported by ONR grants N00014-09-1-1044 and N00014-06-1-0734, a gift from Microsoft Corporation, and an Okawa Foundation Research Grant.  ... 
dblp:conf/icml/GomesK10 fatcat:f5dxjrstkvhvzj67n37b6n4fzy

Batch Decorrelation for Active Metric Learning [article]

Priyadarshini K, Ritesh Goru, Siddhartha Chaudhuri, Subhasis Chaudhuri
2020 arXiv   pre-print
Experiments indicate our method is general, adaptable, and outperforms the state-of-the-art.  ...  We find that standard active learning approaches degrade when annotations are requested for batches of triplets at a time: our studies suggest that correlation among triplets is responsible.  ...  ., 1997] , gives a near-optimal solution.  ... 
arXiv:2005.10008v2 fatcat:5dacudmo25didelhmaav2peo3m

Batch Mode Active Learning for Multimedia Pattern Recognition

Shayok Chakraborty, Vineeth Balasubramanian, Sethuraman Panchanathan
2012 2012 IEEE International Symposium on Multimedia  
This has expanded the possibility of solving real world problems using computational learning frameworks.  ...  However, while gathering a large amount of data is cheap and easy, annotating them with class labels is an expensive process in terms of time, labor and human expertise.  ...  ACKNOWLEDGEMENTS My tenure at Arizona State University has been influenced and guided by a number of people to whom I am deeply indebted.  ... 
doi:10.1109/ism.2012.101 dblp:conf/ism/ChakrabortyBP12 fatcat:kvr4sjlulrcv5cdwtrapadskm4

Subset Replay Based Continual Learning for Scalable Improvement of Autonomous Systems

Pratik Prabhanjan Brahma, Adrienne Othon
2018 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)  
In this work, we show that carefully choosing a small subset of the older data with the objective of promoting representativeness and diversity can also help in learning continuously.  ...  While machine learning techniques have come a long way in showing astounding performance on various vision problems, the conventional way of training is not applicable for learning from a sequence of new  ...  Submodular functions for subset selection Various clustering algorithms, like k-medoids, can be connected to submodular optimization.  ... 
doi:10.1109/cvprw.2018.00154 dblp:conf/cvpr/BrahmaO18 fatcat:cehhsc4zc5btfkzinh3glhpoli
« Previous Showing results 1 — 15 out of 139 results