I
Irina Rish
Researcher at Université de Montréal
Publications - 221
Citations - 7792
Irina Rish is an academic researcher from Université de Montréal. The author has contributed to research in topics: Computer science & Approximation algorithm. The author has an hindex of 34, co-authored 198 publications receiving 6830 citations. Previous affiliations of Irina Rish include IBM & University of California, Irvine.
Papers
More filters
Patent
Transductive lasso for high-dimensional data regression problems
Dan He,Laxmi Parida,Irina Rish +2 more
TL;DR: In this article, a set of training samples and test samples are received, and a first centered Gram matrix of a given dimension is determined for each feature vector that include at least one of the training samples.
Patent
Presentation of websites to a computer user
TL;DR: In this article, a profile of a computer user is obtained that contains meta tags descriptive of the participants of a first social networking website and a profile from the second social network website is selected.
Proceedings ArticleDOI
Blind source separation approach to performance diagnosis and dependency discovery
Gaurav Chandalia,Irina Rish +1 more
TL;DR: This work proposes an approach to problem diagnosis and dependency discovery from end-to-end performance measurements in cases when the dependency/routing information is unknown or partially known, and applies sparse non-negative matrix factorization techniques that appear particularly fitted to the problem of recovering network bottlenecks and dependency (routing) matrix.
Posted Content
Adversarial Feature Desensitization
TL;DR: Adversarial Feature Desensitization (AFD) is proposed to improve network robustness to input perturbations via an adversarial training procedure which has better generalization ability and is substantially improving the state-of-the-art in robust classification against previously observed adversarial attacks.
Journal Article
Gradient Masked Averaging for Federated Learning
Irene Tenison,Sai Aravind Sreeramadas,Vaikkunth Mugunthan,Edouard Oyallon,Eugene Belilovsky,Irina Rish +5 more
TL;DR: This work proposes a gradient masked averaging approach for federated learning as an alternative to the standard averaging of client updates, which can be adapted as a drop-in replacement in most existing federated algorithms.