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
Sparse Markov Net Learning with Priors on Regularization Parameters
TL;DR: In this article, a Bayesian approach is adopted, treating the regularization parameters as random variable(s) with some prior, and using MAP optimization to find both the inverse covariance matrix and the unknown regularization parameter.
Journal ArticleDOI
Scaling the Number of Tasks in Continual Learning
Timothée Lesort,Oleksiy Ostapenko,Diganta Misra,Md Rifat Arefin,P. Rodr'iguez,Laurent Charlin,Irina Rish +6 more
TL;DR: Stochastic gradient descent can learn, progress, and converge to a solution that according to existing literature needs a continual learning algorithm, and a new experimentation framework, SCoLe (Scaling Continual Learning), is proposed to study the knowledge retention and accumulation of algorithms in potentially infinite sequences of tasks.
Patent
Recovering the structure of sparse markov networks from high-dimensional data
Narges Bani Asadi,Guillermo A. Cecchi,Dimitri Kanevsky,Bhuvana Ramabhadran,Irina Rish,Katya Scheinberg +5 more
TL;DR: In this article, a first dataset is received that includes a first set of physical world data and a decision associated with the second dataset based on the at least one data model is generated in response to the probability being above a given threshold.
Patent
Method and apparatus for representing and generating evaluation functions in a data classification system
TL;DR: In this article, a unified framework is disclosed for representing and generating evaluation functions for a classification system, which is based on a set of configurable parameters and is a function of the distance between examples.
Posted Content
Invariance Principle Meets Information Bottleneck for Out-of-Distribution Generalization
TL;DR: The authors showed that the invariance principle alone alone is insufficient to generalize OOD and proposed a form of information bottleneck constraint along with invariance to solve the OOD generalization problem.