Multi-distribution learning is a natural generalization of PAC learning ...
We study a problem of best-effort adaptation motivated by several
applic...
For traffic routing platforms, the choice of which route to recommend to...
Adversarial robustness is a key desirable property of neural networks. I...
We provide a convergence analysis of gradient descent for the problem of...
In this paper, we propose a natural notion of individual preference (IP)...
We study the problem of learning generalized linear models under adversa...
We present a detailed study of estimation errors in terms of surrogate l...
Recent investigations in noise contrastive estimation suggest, both
empi...
Suppose we are given two datasets: a labeled dataset and unlabeled datas...
We investigate approximation guarantees provided by logistic regression ...
Adversarial robustness is a critical property in a variety of modern mac...
We present polynomial time and sample efficient algorithms for learning ...
We advocate for a practical Maximum Likelihood Estimation (MLE) approach...
Labelled data often comes at a high cost as it may require recruiting hu...
We investigate the problem of active learning in the streaming setting i...
We present a more general analysis of H-calibration for adversarially
ro...
Adversarial robustness is an increasingly critical property of classifie...
Alongside the well-publicized accomplishments of deep neural networks th...
Training and evaluation of fair classifiers is a challenging problem. Th...
Adversarial robustness corresponds to the susceptibility of deep neural
...
We present a new data-driven model of fairness that, unlike existing sta...
Linear predictors form a rich class of hypotheses used in a variety of
l...
Existing methods for reducing disparate performance of a classifier acro...
A common distinction in fair machine learning, in particular in fair
cla...
Robustness is a key requirement for widespread deployment of machine lea...
Adversarial or test time robustness measures the susceptibility of a
cla...
In this work we study active learning of homogeneous s-sparse halfspaces...
We study the role of depth in training randomly initialized overparamete...
Adversarial or test time robustness measures the susceptibility of a mac...
We study the design of computationally efficient algorithms with provabl...
Most approaches for ensuring or improving a model's fairness with respec...
Given the widespread popularity of spectral clustering (SC) for partitio...
In data summarization we want to choose k prototypes in order to summari...
We study the notion of Bilu-Linial stability in the context of Independe...
Dictionary learning is a popular approach for inferring a hidden basis o...
Computation of the vertices of the convex hull of a set S of n points in...
Gaussian mixture models (GMM) are the most widely used statistical model...
Variational inference is a very efficient and popular heuristic used in
...
We introduce a new approach for designing computationally efficient lear...
We introduce a new model of membership query (MQ) learning, where the
le...