354 citations
- Institut national de recherche en sciences et technologies du numériqueFR8 papers
- Indian Institute of Science BangaloreIN5 papers
- Indian Institute of Technology KharagpurIN5 papers
- Microsoft (United States)US5 papers
- Indian Institute of Technology DelhiIN4 papers
- Laboratoire d'Informatique de l'École PolytechniqueFR3 papers
- Microsoft Research (United Kingdom)GB3 papers
- Stanford UniversityUS3 papers
- The University of Texas at AustinUS3 papers
- Carnegie Mellon UniversityUS2 papers
- Duke UniversityUS2 papers
- Geometric (India)IN2 papers
4 papers · 1 filter
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…
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…
Pyramid: Enhancing Selectivity in Big Data Protection with Count Featurization
Mathias Lecuyer, Riley Spahn, Roxana Geambasu +2
Protecting vast quantities of data poses a daunting challenge for the growing number of organizations that collect, stockpile, and monetize it. The ability to distinguish data that…
How to Escape Saddle Points Efficiently
Chi Jin, Rong Ge, Praneeth Netrapalli +2
This paper shows that a perturbed form of gradient descent converges to a second-order stationary point in a number iterations which depends only poly-logarithmically on dimension…