More Like this

1. PAC-Wrap: Semi-Supervised PAC Anomaly Detection

   Ji, X.; Li, S.; Dobriban, E.; Sokolsky, O.; Lee I. (June 2022, KDD)
2. Collaborative PAC Learning

   Blum, Avrim; Haghtalab, Nika; Procaccia, Ariel D; Qiao, Mingda (December 2017, NIPS 2017)

   We consider a collaborative PAC learning model, in which k players attempt to learn the same underlying concept. We ask how much more information is required to learn an accurate classifier for all players simultaneously. We refer to the ratio between the sample complexity of collaborative PAC learning and its non-collaborative (single-player) counterpart as the overhead. We design learning algorithms with O(ln(k)) and O(ln2 (k)) overhead in the personalized and centralized variants our model. This gives an exponential improvement upon the naïve algorithm that does not share information among players. We complement our upper bounds with an Ω(ln(k)) overhead lower bound, showing that our results are tight up to a logarithmic factor. 

   more » « less
3. Incentive-Aware PAC Learning

   Zhang, Hanrui; Conitzer, Vincent (January 2021, Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI-21))
4. PAC Learning with Improvements

   Attias, Idan; Blum, Avrim; Naggita, Keziah; Saless, Donya; Sharma, Dravyansh; Walter, Matthew (July 2025, Proceedings of the 42nd International Conference on Machine Learning (ICML))
5. Efficient PAC Learning from the Crowd

   Awasthi, Pranjal; Blum, Avrim: Haghtalab; Mansour, Yishay (January 2017, COLT)

   In recent years crowdsourcing has become the method of choice for gathering labeled training data for learning algorithms. Standard approaches to crowdsourcing view the process of acquiring labeled data separately from the process of learning a classifier from the gathered data. This can give rise to computational and statistical challenges. For example, in most cases there are no known computationally efficient learning algorithms that are robust to the high level of noise that exists in crowdsourced data, and efforts to eliminate noise through voting often require a large number of queries per example. In this paper, we show how by interleaving the process of labeling and learning, we can attain computational efficiency with much less overhead in the labeling cost. In particular, we consider the realizable setting where there exists a true target function in F and consider a pool of labelers. When a noticeable fraction of the labelers are perfect, and the rest behave arbitrarily, we show that any F that can be efficiently learned in the traditional realizable PAC model can be learned in a computationally efficient manner by querying the crowd, despite high amounts of noise in the responses. Moreover, we show that this can be done while each labeler only labels a constant number of examples and the number of labels requested per example, on average, is a constant. When no perfect labelers exist, a related task is to find a set of the labelers which are good but not perfect. We show that we can identify all good labelers, when at least the majority of labelers are good. 

   more » « less