354 citations
- Institut national de recherche en sciences et technologies du numériqueFR8 papers
- Indian Institute of Technology DelhiIN7 papers
- Microsoft (United States)US7 papers
- Indian Institute of Science BangaloreIN6 papers
- Indian Institute of Technology KanpurIN5 papers
- Indian Institute of Technology KharagpurIN5 papers
- Birla Institute of Technology and Science, Pilani - Goa CampusIN4 papers
- Microsoft Research (United Kingdom)GB4 papers
- Carnegie Mellon UniversityUS3 papers
- Geometric (India)IN3 papers
- Laboratoire d'Informatique de l'École PolytechniqueFR3 papers
- Stanford UniversityUS3 papers
Showing 2017 · stat.MLShow all
2 papers · 2 filters
stat.ML2017★ 150 cited
Robust Loss Functions under Label Noise for Deep Neural Networks
Aritra Ghosh, Himanshu Kumar, P. S. Sastry
In many applications of classifier learning, training data suffers from label noise. Deep networks are learned using huge training data where the problem of noisy labels is particu…
stat.ML2017★ 354 cited
Non-convex Optimization for Machine Learning
Prateek Jain, Purushottam Kar
A vast majority of machine learning algorithms train their models and perform inference by solving optimization problems. In order to capture the learning and prediction problems a…