paper-with-me

홈 › Papers

Noise-tolerant, Reliable Active Classification with Comparison Queries

2020-01-15 · Max Hopkins, Daniel Kane, Shachar Lovett, Gaurav Mahajan

With the explosion of massive, widely available unlabeled data in the past years, finding label and time efficient, robust learning algorithms has become ever more important in theory and in practice. We study the paradigm of active learning, in which algorithms with access to large pools of data may adaptively choose what samples to label in the hope of exponentially increasing efficiency. By introducing comparisons, an additional type of query comparing two points, we provide the first time and query efficient algorithms for learning non-homogeneous linear separators robust to bounded (Massart) noise. We further provide algorithms for a generalization of the popular Tsybakov low noise condition, and show how comparisons provide a strong reliability guarantee that is often impractical or impossible with only labels - returning a classifier that makes no errors with high probability.

📄 PDF Abstract BibTeX arXiv:2001.05497

Code (0)

등록된 구현이 없습니다.

Tasks

Active LearningClassificationGeneral Classification

Similar Papers 제목 키워드 기반

Noise-Tolerant Interactive Learning from Pairwise Comparisons

2017-04-19 · Yichong Xu, Hongyang Zhang, Aarti Singh, Kyle Miller 외

We study the problem of interactively learning a binary classifier using noisy labeling and pairwise comparison oracles, where the comparison oracle answers which one in the given two instances is more likely to be posit…

Noise-Tolerant Interactive Learning Using Pairwise Comparisons

2017-12-01 · NeurIPS 2017 12 · Yichong Xu, Hongyang Zhang, Kyle Miller, Aarti Singh 외

We study the problem of interactively learning a binary classifier using noisy labeling and pairwise comparison oracles, where the comparison oracle answers which one in the given two instances is more likely to be posit…

Statistical Active Learning Algorithms for Noise Tolerance and Differential Privacy

2013-07-11 · Maria Florina Balcan, Vitaly Feldman

We describe a framework for designing efficient active learning algorithms that are tolerant to random classification noise and are differentially-private. The framework is based on active learning algorithms that are st…

Active LearningGeneral Classification

Statistical Active Learning Algorithms

2013-12-01 · NeurIPS 2013 12 · Maria-Florina F. Balcan, Vitaly Feldman

We describe a framework for designing efficient active learning algorithms that are tolerant to random classification noise. The framework is based on active learning algorithms that are statistical in the sense that the…

Active LearningGeneral Classification

Fault-Tolerant Neural Networks from Biological Error Correction Codes

2022-02-25 · Alexander Zlokapa, Andrew K. Tan, John M. Martyn, Ila R. Fiete 외

It has been an open question in deep learning if fault-tolerant computation is possible: can arbitrarily reliable computation be achieved using only unreliable neurons? In the grid cells of the mammalian cortex, analog e…

Open-Ended Question Answering