Search Results for author: Shai Ben-David

Found 22 papers, 1 papers with code

Impossibility results for fair representations

no code implementations7 Jul 2021 Tosca Lechner, Shai Ben-David, Sushant Agarwal, Nivasini Ananthakrishnan

The goal of such representations is that a model trained on data under the representation (e. g., a classifier) will be guaranteed to respect some fairness constraints.


Impossibility results for fair representation

no code implementations NeurIPS 2021 Tosca Lechner, Nivasini Ananthakrishnan, Sushant Agarwal, Shai Ben-David

With the growing awareness to fairness in machine learning and the realization of the central role that data representation has in data processing tasks, there is an obvious interest in notions of fair data representations.


Enforcing Interpretability and its Statistical Impacts: Trade-offs between Accuracy and Interpretability

no code implementations26 Oct 2020 Gintare Karolina Dziugaite, Shai Ben-David, Daniel M. Roy

We then model the act of enforcing interpretability as that of performing empirical risk minimization over the set of interpretable hypotheses.

Learning Theory

When can unlabeled data improve the learning rate?

no code implementations28 May 2019 Christina Göpfert, Shai Ben-David, Olivier Bousquet, Sylvain Gelly, Ilya Tolstikhin, Ruth Urner

In semi-supervised classification, one is given access both to labeled and unlabeled data.

Nearly tight sample complexity bounds for learning mixtures of Gaussians via sample compression schemes

no code implementations NeurIPS 2018 Hassan Ashtiani, Shai Ben-David, Nicholas Harvey, Christopher Liaw, Abbas Mehrabian, Yaniv Plan

We prove that ϴ(k d^2 / ε^2) samples are necessary and sufficient for learning a mixture of k Gaussians in R^d, up to error ε in total variation distance.

Semi-supervised clustering for de-duplication

no code implementations10 Oct 2018 Shrinu Kushagra, Shai Ben-David, Ihab Ilyas

In this work, we view de-duplication as a clustering problem where the goal is to put records corresponding to the same physical entity in the same cluster and putting records corresponding to different physical entities into different clusters.

Clustering - What Both Theoreticians and Practitioners are Doing Wrong

no code implementations22 May 2018 Shai Ben-David

Unsupervised learning is widely recognized as one of the most important challenges facing machine learning nowa- days.

Model Selection

Empirical Risk Minimization under Fairness Constraints

2 code implementations NeurIPS 2018 Michele Donini, Luca Oneto, Shai Ben-David, John Shawe-Taylor, Massimiliano Pontil

It encourages the conditional risk of the learned classifier to be approximately constant with respect to the sensitive variable.


Provably noise-robust, regularised $k$-means clustering

no code implementations30 Nov 2017 Shrinu Kushagra, Yao-Liang Yu, Shai Ben-David

We focus on the $k$-means objective and we prove that the regularised version of $k$-means is NP-Hard even for $k=1$.

A learning problem that is independent of the set theory ZFC axioms

no code implementations14 Nov 2017 Shai Ben-David, Pavel Hrubes, Shay Moran, Amir Shpilka, Amir Yehudayoff

We consider the following statistical estimation problem: given a family F of real valued functions over some domain X and an i. i. d.

General Classification

Near-optimal Sample Complexity Bounds for Robust Learning of Gaussians Mixtures via Compression Schemes

no code implementations14 Oct 2017 Hassan Ashtiani, Shai Ben-David, Nick Harvey, Christopher Liaw, Abbas Mehrabian, Yaniv Plan

We prove that $\tilde{\Theta}(k d^2 / \varepsilon^2)$ samples are necessary and sufficient for learning a mixture of $k$ Gaussians in $\mathbb{R}^d$, up to error $\varepsilon$ in total variation distance.

Sample-Efficient Learning of Mixtures

no code implementations6 Jun 2017 Hassan Ashtiani, Shai Ben-David, Abbas Mehrabian

Let $\mathcal F$ be an arbitrary class of probability distributions, and let $\mathcal{F}^k$ denote the class of $k$-mixtures of elements of $\mathcal F$.

Density Estimation

Clustering with Same-Cluster Queries

no code implementations NeurIPS 2016 Hassan Ashtiani, Shrinu Kushagra, Shai Ben-David

We show that there is a trade off between computational complexity and query complexity; We prove that for the case of $k$-means clustering (i. e., when the expert conforms to a solution of $k$-means), having access to relatively few such queries allows efficient solutions to otherwise NP hard problems.

Multi-task and Lifelong Learning of Kernels

no code implementations21 Feb 2016 Anastasia Pentina, Shai Ben-David

We consider a problem of learning kernels for use in SVM classification in the multi-task and lifelong scenarios and provide generalization bounds on the error of a large margin classifier.

General Classification Generalization Bounds

Clustering is Easy When ....What?

no code implementations19 Oct 2015 Shai Ben-David

I wish to present a a critical bird's eye overview of the results published on this issue so far and to call attention to the gap between available and desirable results on this issue.

2 Notes on Classes with Vapnik-Chervonenkis Dimension 1

no code implementations19 Jul 2015 Shai Ben-David

Arguably the most influential consequence of the VC analysis is the fundamental theorem of statistical machine learning, stating that a concept class is learnable (in some precise sense) if and only if its VC-dimension is finite.

Learning Theory

Representation Learning for Clustering: A Statistical Framework

no code implementations19 Jun 2015 Hassan Ashtiani, Shai Ben-David

The algorithm designer then uses that sample to come up with a data representation under which $k$-means clustering results in a clustering (of the full data set) that is aligned with the user's clustering.

Representation Learning

Computational Feasibility of Clustering under Clusterability Assumptions

no code implementations2 Jan 2015 Shai Ben-David

In particular, we list some implied requirements for notions of clusterability.

Multiclass learnability and the ERM principle

no code implementations13 Aug 2013 Amit Daniely, Sivan Sabato, Shai Ben-David, Shai Shalev-Shwartz

We study the sample complexity of multiclass prediction in several learning settings.

General Classification

Weighted Clustering

no code implementations8 Sep 2011 Margareta Ackerman, Shai Ben-David, Simina Brânzei, David Loker

One of the most prominent challenges in clustering is "the user's dilemma," which is the problem of selecting an appropriate clustering algorithm for a specific task.

Towards Property-Based Classification of Clustering Paradigms

no code implementations NeurIPS 2010 Margareta Ackerman, Shai Ben-David, David Loker

We propose to address this problem by distilling abstract properties of the input-output behavior of different clustering paradigms.

Classification General Classification

Measures of Clustering Quality: A Working Set of Axioms for Clustering

no code implementations NeurIPS 2008 Shai Ben-David, Margareta Ackerman

In this respect, we follow up on the work of Kelinberg, (Kleinberg) that showed an impossibility result for such axiomatization.


Cannot find the paper you are looking for? You can Submit a new open access paper.