Fetching the paper…
Reading the bibliography…
We consider a binary classification problem when the data comes from a mixture of two rotationally symmetric distributions satisfying concentration and anti-concentration properties enjoyed by log-concave distributions among others.
Probability of error of some adaptive pattern-recognition machines
Scudder, H · 1965
Earlier work this paper cites.
On the exponential value of labeled samples
Castelli, V · 1995
Earlier work this paper cites.
Unsupervised word sense disambiguation rivaling supervised methods
Yarowsky, D · 1995
Earlier work this paper cites.
The relative value of labeled and unlabeled samples in pattern recognition in the regular parametric case,” in preparation
Castelli, V · 1996
Earlier work this paper cites.
D.: Does unlabeled data provably help? worst-case analysis of the sample complexity of semi-supervised learning
Ben-David, S · 2008
Earlier work this paper cites.
Predicting what you already know helps: Provable self-supervised learning
Lee, J. D · 2008
Earlier work this paper cites.
Unlabeled data: Now it helps, now it doesn't
Singh, A · 2009
Earlier work this paper cites.
Introduction to semi-supervised learning
Zhu, X · 2009
Earlier work this paper cites.
A discriminative model for semi-supervised learning
Balcan, M.-F · 2010
Earlier work this paper cites.
Semi-Supervised Learning
Chapelle, O · 2010
Earlier work this paper cites.
Introduction to the non-asymptotic analysis of random matrices
Vershynin, R · 2010
Cited alongside, same era.
Unlabeled Data Does Provably Help
Darnstädt, M · 2013
Cited alongside, same era.
Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks
Lee, D.-H · 2013
Cited alongside, same era.
Distilling the knowledge in a neural network
Hinton, G · 2015
Cited alongside, same era.
Minimax Gaussian Classification & Clustering
Li, T · 2017
Cited alongside, same era.
BERT: Pre-training of deep bidirectional transformers for language understanding
Devlin, J · 2019
Cited alongside, same era.
Understanding and mitigating the tradeoff between robustness and accuracy
Raghunathan, A · 2020
Later among the works it cites.
A theory of label propagation for subpopulation shift
Cai, T · 2021
Closest in time.
Generalization bounds via distillation
Hsu, D · 2021
Closest in time.
Statistical and algorithmic insights for semi-supervised learning with self-training
Oymak, S · 2021
Closest in time.
Meta pseudo labels
Pham, H · 2021
Closest in time.
In defense of pseudo-labeling: An uncertainty-aware pseudo-label selection framework for semi-supervised learning
Rizve, M. N · 2021
Closest in time.
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Distribution-independent pac learning of halfspaces with massart noise
Diakonikolas, I · 2019
Cited alongside, same era.
When can unlabeled data improve the learning rate?
Göpfert, C · 2019
Cited alongside, same era.
Confidence regularized self-training
Zou, Y · 2019
Cited alongside, same era.
Understanding self-training for gradual domain adaptation
Kumar, A · 2020
Cited alongside, same era.
A simple framework for contrastive learning of visual representations
Chen, T
Cited in the paper.
Self-training avoids using spurious features under domain shift
Chen, Y
Cited in the paper.
Tosh, C · 2021
Closest in time.
Theoretical analysis of self-training with deep networks on unlabeled data
Wei, C · 2021
Closest in time.
In-n-out: Pre-training and self-training using auxiliary information for out-of-distribution robustness
Xie, S. M · 2021
Closest in time.
Provable robustness of adversarial training for learning halfspaces with noise
Zou, D · 2021
Closest in time.