A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is
Correspondence to: Ruth Urner <firstname.lastname@example.org>. ... 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
Encyclopedia of Algorithms
Urner et al.  proved label complexity reductions with this paradigm under a distributional assumption. ...doi:10.1007/978-1-4939-2864-4_769 fatcat:amdxmajq6zcnnn3zlhrtmeoddq
Encyclopedia of Algorithms
Urner et al.  proved label complexity reductions with this paradigm under a distributional assumption. ...doi:10.1007/978-3-642-27848-8_769-2 fatcat:5hcjmipp4rcb7pn2654b2zn5se
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 thearXiv:1503.03594v1 fatcat:l6lpjpr6uzaxlgftqon4hc6qwm
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.
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 providingarXiv:1407.7937v1 fatcat:2gm6jningbbctctyo5nekdrgta
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.
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 optimizationdblp:conf/icml/WulffUB13 fatcat:ayvpaon2bfcqjb7ps4t7ap5flm
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.
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 maydblp:journals/jmlr/UrnerBS12 fatcat:t74l4kdtybhstdsxvexceg55ma
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.
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 anydblp:conf/nips/PentinaU16 fatcat:xo7smmtxvfehnliljk4awj3mbm
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.
., 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
(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
Ruth Urner and Hassan Ashtiani were supported by NSERC Discovery Grants. ...arXiv:2006.16520v2 fatcat:zbbxo3rimzfanoaqzok75ovpbe
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. OurarXiv:1309.6811v1 fatcat:dyg2e5sya5clpmlpkayr6ohc4i
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.
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
Urner. ... The lemma was shown in Urner ( 2013 ), but has not been published before. ...dblp:conf/colt/Ben-DavidU14 fatcat:pe6k2gwedvhc5bk3nkpjrxsrxy
Lecture Notes in Computer Science
A recent line of work, starting with Beigman and Vohra  and Zadimoghaddam and Roth , 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 sampledoi:10.1007/978-3-319-13129-0_28 fatcat:saohowj4cvh5hjychvoce6kjwa
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  . 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.
« Previous Showing results 1 — 15 out of 331 results