Finite-sample analysis of interpolating linear classifiers in the overparameterized regime

NS Chatterji, PM Long - Journal of Machine Learning Research, 2021‏ - jmlr.org
We prove bounds on the population risk of the maximum margin algorithm for two-class
linear classification. For linearly separable training data, the maximum margin algorithm has …

Equalized odds postprocessing under imperfect group information

P Awasthi, M Kleindessner… - … conference on artificial …, 2020‏ - proceedings.mlr.press
Most approaches aiming to ensure a model's fairness with respect to a protected attribute
(such as gender or race) assume to know the true value of the attribute for every data point …

Strength from weakness: Fast learning using weak supervision

J Robinson, S Jegelka, S Sra - International Conference on …, 2020‏ - proceedings.mlr.press
We study generalization properties of weakly supervised learning, that is, learning where
only a few" strong" labels (the actual target for prediction) are present but many more" weak" …

Adversarial crowdsourcing through robust rank-one matrix completion

Q Ma, A Olshevsky - Advances in Neural Information …, 2020‏ - proceedings.neurips.cc
We consider the problem of reconstructing a rank-one matrix from a revealed subset of its
entries when some of the revealed entries are corrupted with perturbations that are unknown …

Crowdsourced label aggregation using bilayer collaborative clustering

J Zhang, VS Sheng, J Wu - IEEE transactions on neural …, 2019‏ - ieeexplore.ieee.org
With online crowdsourcing platforms, labels can be acquired at relatively low costs from
massive nonexpert workers. To improve the quality of labels obtained from these imperfect …

Eliciting confidence for improving crowdsourced audio annotations

AE Méndez Méndez, M Cartwright, JP Bello… - Proceedings of the ACM …, 2022‏ - dl.acm.org
In this work we explore confidence elicitation methods for crowdsourcing" soft" labels, eg,
probability estimates, to reduce the annotation costs for domains with ambiguous data …

CONAN: A framework for detecting and handling collusion in crowdsourcing

P Chen, H Sun, Y Fang, X Liu - Information Sciences, 2020‏ - Elsevier
In contrast to the traditional view that individuals should work independently to realize the
crowd wisdom, crowdsourcing workers often collaborate with each other in task processing …

Ranking and combining latent structured predictive scores without labeled data

S Afshar, Y Chen, S Han, Y Lin - IISE Transactions, 2024‏ - Taylor & Francis
Combining multiple predictors obtained from distributed data sources to an accurate meta-
learner is promising to achieve enhanced performance in lots of prediction problems. As the …

Online algorithm for unsupervised sensor selection

A Verma, M Hanawal, C Szepesvari… - The 22nd …, 2019‏ - proceedings.mlr.press
In many security and healthcare systems, the detection and diagnosis systems use a
sequence of sensors/tests. Each test outputs a prediction of the latent state and carries an …

Robust Decision Aggregation with Adversarial Experts

Y Guo, Y Kong - arxiv preprint arxiv:2403.08222, 2024‏ - arxiv.org
We consider a binary decision aggregation problem in the presence of both truthful and
adversarial experts. The truthful experts will report their private signals truthfully with proper …