Filters








331 Hits in 1.4 sec

On the (Un-)Avoidability of Adversarial Examples [article]

Sadia Chowdhury, Ruth Urner
2021 arXiv   pre-print
Correspondence to: Ruth Urner <ruth@eecs.yorku.ca>.  ...  The margin rate is related the notion of Probabilistic Lipschitzness (Urner et al., 2013) and the geometric noise exponent (Steinwart & Scovel, 2007) .  ... 
arXiv:2106.13326v1 fatcat:draernshq5hy3fbxoekpnzrofq

Active Learning – Modern Learning Theory [chapter]

Maria-Florina Balcan, Ruth Urner
2016 Encyclopedia of Algorithms  
Urner et al. [12] proved label complexity reductions with this paradigm under a distributional assumption.  ... 
doi:10.1007/978-1-4939-2864-4_769 fatcat:amdxmajq6zcnnn3zlhrtmeoddq

Active Learning - Modern Learning Theory [chapter]

Maria-Florina Balcan, Ruth Urner
2014 Encyclopedia of Algorithms  
Urner et al. [12] proved label complexity reductions with this paradigm under a distributional assumption.  ... 
doi:10.1007/978-3-642-27848-8_769-2 fatcat:5hcjmipp4rcb7pn2654b2zn5se

Efficient Learning of Linear Separators under Bounded Noise [article]

Pranjal Awasthi, Maria-Florina Balcan, Nika Haghtalab, Ruth Urner
2015 arXiv   pre-print
We study the learnability of linear separators in ^d in the presence of bounded (a.k.a Massart) noise. This is a realistic generalization of the random classification noise model, where the adversary can flip each example x with probability η(x) ≤η. We provide the first polynomial time algorithm that can learn linear separators to arbitrarily small excess error in this noise model under the uniform distribution over the unit ball in ^d, for some constant value of η. While widely studied in the
more » ... tatistical learning theory community in the context of getting faster convergence rates, computationally efficient algorithms in this model had remained elusive. Our work provides the first evidence that one can indeed design algorithms achieving arbitrarily small excess error in polynomial time under this realistic noise model and thus opens up a new and exciting line of research. We additionally provide lower bounds showing that popular algorithms such as hinge loss minimization and averaging cannot lead to arbitrarily small excess error under Massart noise, even under the uniform distribution. Our work instead, makes use of a margin based technique developed in the context of active learning. As a result, our algorithm is also an active learning algorithm with label complexity that is only a logarithmic the desired excess error ϵ.
arXiv:1503.03594v1 fatcat:l6lpjpr6uzaxlgftqon4hc6qwm

Learning Economic Parameters from Revealed Preferences [article]

Maria-Florina Balcan, Amit Daniely, Ruta Mehta, Ruth Urner, Vijay V. Vazirani
2014 arXiv   pre-print
A recent line of work, starting with Beigman and Vohra (2006) and Zadimoghaddam and Roth (2012), has addressed the problem of learning a utility function from revealed preference data. The goal here is to make use of past data describing the purchases of a utility maximizing agent when faced with certain prices and budget constraints in order to produce a hypothesis function that can accurately forecast the future behavior of the agent. In this work we advance this line of work by providing
more » ... le complexity guarantees and efficient algorithms for a number of important classes. By drawing a connection to recent advances in multi-class learning, we provide a computationally efficient algorithm with tight sample complexity guarantees (Θ(d/ϵ) for the case of d goods) for learning linear utility functions under a linear price model. This solves an open question in Zadimoghaddam and Roth (2012). Our technique yields numerous generalizations including the ability to learn other well-studied classes of utility functions, to deal with a misspecified model, and with non-linear prices.
arXiv:1407.7937v1 fatcat:2gm6jningbbctctyo5nekdrgta

Monochromatic Bi-Clustering

Sharon Wulff, Ruth Urner, Shai Ben-David
2013 International Conference on Machine Learning  
We propose a natural cost function for the bi-clustering task, the monochromatic cost. This cost function is suitable for detecting meaningful homogeneous bi-clusters based on categorical valued input matrices. Such tasks arise in many applications, such as the analysis of social networks and in systemsbiology where researchers try to infer functional grouping of biological agents based on their pairwise interactions. We analyze the computational complexity of the resulting optimization
more » ... We present a polynomial time approximation algorithm for this bi-clustering task and complement this result by showing that finding (exact) optimal solutions is NP-hard. As far as we know, these are the first positive approximation guarantees and formal NP-hardness results for any bi-clustering optimization problem. In addition, we show that our optimization problem can be efficiently solved by deterministic annealing, yielding a promising heuristic for large problem instances.
dblp:conf/icml/WulffUB13 fatcat:ayvpaon2bfcqjb7ps4t7ap5flm

Learning from Weak Teachers

Ruth Urner, Shai Ben-David, Ohad Shamir
2012 Journal of machine learning research  
This paper addresses the problem of learning when high-quality labeled examples are an expensive resource, while samples with error-prone labeling (for example generated by crowdsourcing) are readily available. We introduce a formal framework for such learning scenarios with label sources of varying quality, and we propose a parametric model for such label sources ("weak teachers"), reflecting the intuition that their labeling is likely to be correct in label-homogeneous regions but may
more » ... ate near classification boundaries. We consider learning when the learner has access to weakly labeled random samples and, on top of that, can actively query the correct labels of sample points of its choice. We propose a learning algorithm for this scenario, analyze its sample complexity and prove that, under certain conditions on the underlying data distribution, our learner can utilize the weak labels to reduce the number of expert labels it requires. We view this paper as a first step towards the development of a theory of learning from labels generated by teachers of varying accuracy, a scenario that is relevant in various practical applications.
dblp:journals/jmlr/UrnerBS12 fatcat:t74l4kdtybhstdsxvexceg55ma

Lifelong Learning with Weighted Majority Votes

Anastasia Pentina, Ruth Urner
2016 Neural Information Processing Systems  
Better understanding of the potential benefits of information transfer and representation learning is an important step towards the goal of building intelligent systems that are able to persist in the world and learn over time. In this work, we consider a setting where the learner encounters a stream of tasks but is able to retain only limited information from each encountered task, such as a learned predictor. In contrast to most previous works analyzing this scenario, we do not make any
more » ... butional assumptions on the task generating process. Instead, we formulate a complexity measure that captures the diversity of the observed tasks. We provide a lifelong learning algorithm with error guarantees for every observed task (rather than on average). We show sample complexity reductions in comparison to solving every task in isolation in terms of our task complexity measure. Further, our algorithmic framework can naturally be viewed as learning a representation from encountered tasks with a neural network.
dblp:conf/nips/PentinaU16 fatcat:xo7smmtxvfehnliljk4awj3mbm

Active Nearest Neighbors in Changing Environments

Christopher Berlind, Ruth Urner
2015 International Conference on Machine Learning  
., 2008; Ben-David & Urner, 2014; Shi & Sha, 2012) .  ...  A 1-nearest neighbor algorithm has been analyzed under covariate shift (Ben-David & Urner, 2014); however, in contrast to our work, that study assumes a lower bound on a weight ratio between source and  ... 
dblp:conf/icml/BerlindU15 fatcat:ciznljydgrebrjo6d7hgi3c5zu

PLAL: Cluster-based active learning

Ruth Urner, Sharon Wulff, Shai Ben-David
2013 Annual Conference Computational Learning Theory  
(Urner et al., 2011b) introduced the version employed here and applied it to formally establish benefits of unlabeled data for semi-supervised learning (Urner et al., 2011b) .  ...  We We adapt a proof from Urner et al. (2011b) for the success of the 1-Nearest Neighbor algorithm under Lipschitzness to its modified version of 1-NN with PLAL.  ... 
dblp:conf/colt/UrnerWB13 fatcat:kkxpannikfe2pkuq7x6cliaejm

Black-box Certification and Learning under Adversarial Perturbations [article]

Hassan Ashtiani, Vinayak Pathak, Ruth Urner
2022 arXiv   pre-print
Ruth Urner and Hassan Ashtiani were supported by NSERC Discovery Grants.  ... 
arXiv:2006.16520v2 fatcat:zbbxo3rimzfanoaqzok75ovpbe

Generative Multiple-Instance Learning Models For Quantitative Electromyography [article]

Tameem Adel, Benn Smith, Ruth Urner, Daniel Stashuk, Daniel J. Lizotte
2013 arXiv   pre-print
We present a comprehensive study of the use of generative modeling approaches for Multiple-Instance Learning (MIL) problems. In MIL a learner receives training instances grouped together into bags with labels for the bags only (which might not be correct for the comprised instances). Our work was motivated by the task of facilitating the diagnosis of neuromuscular disorders using sets of motor unit potential trains (MUPTs) detected within a muscle which can be cast as a MIL problem. Our
more » ... leads to a state-of-the-art solution to the problem of muscle classification. By introducing and analyzing generative models for MIL in a general framework and examining a variety of model structures and components, our work also serves as a methodological guide to modelling MIL tasks. We evaluate our proposed methods both on MUPT datasets and on the MUSK1 dataset, one of the most widely used benchmarks for MIL.
arXiv:1309.6811v1 fatcat:dyg2e5sya5clpmlpkayr6ohc4i

Foundations of Unsupervised Learning (Dagstuhl Seminar 16382)

Maria-Florina Balcan, Shai Ben-David, Ruth Urner, Ulrike Von Luxburg, Marc Herbstritt
2017 Dagstuhl Reports  
Lifelong Learning with Weighted Majority Votes Ruth Urner . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . A Modular Theory of Feature Learning Robert C.  ...  URL http://www.stat.washington.edu/research/reports/2014/tr624.pdf Linear Algebraic Structure of Word Meanings Executive summaryRuth Urner and Shai Ben-David . .... . . . . . . . . . . . . . . . .  ... 
doi:10.4230/dagrep.6.9.94 dblp:journals/dagstuhl-reports/BalcanBUL16 fatcat:gliqlrxzyrbzffssk5t3udw54q

The sample complexity of agnostic learning under deterministic labels

Shai Ben-David, Ruth Urner
2014 Annual Conference Computational Learning Theory  
Urner.  ...  The lemma was shown in Urner ( 2013 ), but has not been published before.  ... 
dblp:conf/colt/Ben-DavidU14 fatcat:pe6k2gwedvhc5bk3nkpjrxsrxy

Learning Economic Parameters from Revealed Preferences [chapter]

Maria-Florina Balcan, Amit Daniely, Ruta Mehta, Ruth Urner, Vijay V. Vazirani
2014 Lecture Notes in Computer Science  
A recent line of work, starting with Beigman and Vohra [4] and Zadimoghaddam and Roth [27], has addressed the problem of learning a utility function from revealed preference data. The goal here is to make use of past data describing the purchases of a utility maximizing agent when faced with certain prices and budget constraints in order to produce a hypothesis function that can accurately forecast the future behavior of the agent. In this work we advance this line of work by providing sample
more » ... mplexity guarantees and efficient algorithms for a number of important classes. By drawing a connection to recent advances in multi-class learning, we provide a computationally efficient algorithm with tight sample complexity guarantees (Θ(d/ ) for the case of d goods) for learning linear utility functions under a linear price model. This solves an open question in Zadimoghaddam and Roth [27] . Our technique yields numerous generalizations including the ability to learn other well-studied classes of utility functions, to deal with a misspecified model, and with non-linear prices.
doi:10.1007/978-3-319-13129-0_28 fatcat:saohowj4cvh5hjychvoce6kjwa
« Previous Showing results 1 — 15 out of 331 results