Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Irina Rish

Irina Rish

Approximate Bayesian Optimisation for Neural Networks


Aug 31, 2021
Nadhir Hassen, Irina Rish

Figure 1 for Approximate Bayesian Optimisation for Neural Networks
Figure 2 for Approximate Bayesian Optimisation for Neural Networks
Figure 3 for Approximate Bayesian Optimisation for Neural Networks
Figure 4 for Approximate Bayesian Optimisation for Neural Networks
* 9 pages with 4 pages supplementary materials 
  Access Paper or Ask Questions

Sequoia: A Software Framework to Unify Continual Learning Research


Aug 03, 2021
Fabrice Normandin, Florian Golemo, Oleksiy Ostapenko, Pau Rodriguez, Matthew D Riemer, Julio Hurtado, Khimya Khetarpal, Dominic Zhao, Ryan Lindeborg, Timothée Lesort, Laurent Charlin, Irina Rish, Massimo Caccia

Figure 1 for Sequoia: A Software Framework to Unify Continual Learning Research
Figure 2 for Sequoia: A Software Framework to Unify Continual Learning Research
Figure 3 for Sequoia: A Software Framework to Unify Continual Learning Research
Figure 4 for Sequoia: A Software Framework to Unify Continual Learning Research

  Access Paper or Ask Questions

Parametric Scattering Networks


Jul 20, 2021
Shanel Gauthier, Benjamin Thérien, Laurent Alsène-Racicot, Irina Rish, Eugene Belilovsky, Michael Eickenberg, Guy Wolf

Figure 1 for Parametric Scattering Networks
Figure 2 for Parametric Scattering Networks
Figure 3 for Parametric Scattering Networks
Figure 4 for Parametric Scattering Networks
* 6 pages, 4 tables, 2 figures 
  Access Paper or Ask Questions

Invariance Principle Meets Information Bottleneck for Out-of-Distribution Generalization


Jun 11, 2021
Kartik Ahuja, Ethan Caballero, Dinghuai Zhang, Yoshua Bengio, Ioannis Mitliagkas, Irina Rish

Figure 1 for Invariance Principle Meets Information Bottleneck for Out-of-Distribution Generalization
Figure 2 for Invariance Principle Meets Information Bottleneck for Out-of-Distribution Generalization
Figure 3 for Invariance Principle Meets Information Bottleneck for Out-of-Distribution Generalization
Figure 4 for Invariance Principle Meets Information Bottleneck for Out-of-Distribution Generalization

  Access Paper or Ask Questions

SAND-mask: An Enhanced Gradient Masking Strategy for the Discovery of Invariances in Domain Generalization


Jun 04, 2021
Soroosh Shahtalebi, Jean-Christophe Gagnon-Audet, Touraj Laleh, Mojtaba Faramarzi, Kartik Ahuja, Irina Rish

Figure 1 for SAND-mask: An Enhanced Gradient Masking Strategy for the Discovery of Invariances in Domain Generalization
Figure 2 for SAND-mask: An Enhanced Gradient Masking Strategy for the Discovery of Invariances in Domain Generalization
Figure 3 for SAND-mask: An Enhanced Gradient Masking Strategy for the Discovery of Invariances in Domain Generalization
Figure 4 for SAND-mask: An Enhanced Gradient Masking Strategy for the Discovery of Invariances in Domain Generalization

  Access Paper or Ask Questions

Continual Learning in Deep Networks: an Analysis of the Last Layer


Jun 03, 2021
Timothée Lesort, Thomas George, Irina Rish

Figure 1 for Continual Learning in Deep Networks: an Analysis of the Last Layer
Figure 2 for Continual Learning in Deep Networks: an Analysis of the Last Layer
Figure 3 for Continual Learning in Deep Networks: an Analysis of the Last Layer
Figure 4 for Continual Learning in Deep Networks: an Analysis of the Last Layer

  Access Paper or Ask Questions

Gradient Masked Federated Optimization


Apr 21, 2021
Irene Tenison, Sreya Francis, Irina Rish

Figure 1 for Gradient Masked Federated Optimization
Figure 2 for Gradient Masked Federated Optimization
Figure 3 for Gradient Masked Federated Optimization
Figure 4 for Gradient Masked Federated Optimization
* ICLR 2021 Distributed and Private Machine Learning(DPML) Workshop 
  Access Paper or Ask Questions

Towards Causal Federated Learning For Enhanced Robustness and Privacy


Apr 14, 2021
Sreya Francis, Irene Tenison, Irina Rish

Figure 1 for Towards Causal Federated Learning For Enhanced Robustness and Privacy
Figure 2 for Towards Causal Federated Learning For Enhanced Robustness and Privacy
Figure 3 for Towards Causal Federated Learning For Enhanced Robustness and Privacy
* ICLR 2021 Distributed and Private Machine Learning(DPML) Workshop 
  Access Paper or Ask Questions

Understanding Continual Learning Settings with Data Distribution Drift Analysis


Apr 04, 2021
Timothée Lesort, Massimo Caccia, Irina Rish

Figure 1 for Understanding Continual Learning Settings with Data Distribution Drift Analysis
Figure 2 for Understanding Continual Learning Settings with Data Distribution Drift Analysis
Figure 3 for Understanding Continual Learning Settings with Data Distribution Drift Analysis

  Access Paper or Ask Questions

Towards Continual Reinforcement Learning: A Review and Perspectives


Dec 25, 2020
Khimya Khetarpal, Matthew Riemer, Irina Rish, Doina Precup

Figure 1 for Towards Continual Reinforcement Learning: A Review and Perspectives
Figure 2 for Towards Continual Reinforcement Learning: A Review and Perspectives
Figure 3 for Towards Continual Reinforcement Learning: A Review and Perspectives
Figure 4 for Towards Continual Reinforcement Learning: A Review and Perspectives
* Preprint, 52 pages, 8 figures 
  Access Paper or Ask Questions

COVI-AgentSim: an Agent-based Model for Evaluating Methods of Digital Contact Tracing


Oct 30, 2020
Prateek Gupta, Tegan Maharaj, Martin Weiss, Nasim Rahaman, Hannah Alsdurf, Abhinav Sharma, Nanor Minoyan, Soren Harnois-Leblanc, Victor Schmidt, Pierre-Luc St. Charles, Tristan Deleu, Andrew Williams, Akshay Patel, Meng Qu, Olexa Bilaniuk, Gaétan Marceau Caron, Pierre Luc Carrier, Satya Ortiz-Gagné, Marc-Andre Rousseau, David Buckeridge, Joumana Ghosn, Yang Zhang, Bernhard Schölkopf, Jian Tang, Irina Rish, Christopher Pal, Joanna Merckx, Eilif B. Muller, Yoshua Bengio

Figure 1 for COVI-AgentSim: an Agent-based Model for Evaluating Methods of Digital Contact Tracing
Figure 2 for COVI-AgentSim: an Agent-based Model for Evaluating Methods of Digital Contact Tracing
Figure 3 for COVI-AgentSim: an Agent-based Model for Evaluating Methods of Digital Contact Tracing
Figure 4 for COVI-AgentSim: an Agent-based Model for Evaluating Methods of Digital Contact Tracing

  Access Paper or Ask Questions

Predicting Infectiousness for Proactive Contact Tracing


Oct 23, 2020
Yoshua Bengio, Prateek Gupta, Tegan Maharaj, Nasim Rahaman, Martin Weiss, Tristan Deleu, Eilif Muller, Meng Qu, Victor Schmidt, Pierre-Luc St-Charles, Hannah Alsdurf, Olexa Bilanuik, David Buckeridge, Gáetan Marceau Caron, Pierre-Luc Carrier, Joumana Ghosn, Satya Ortiz-Gagne, Chris Pal, Irina Rish, Bernhard Schölkopf, Abhinav Sharma, Jian Tang, Andrew Williams

Figure 1 for Predicting Infectiousness for Proactive Contact Tracing
Figure 2 for Predicting Infectiousness for Proactive Contact Tracing
Figure 3 for Predicting Infectiousness for Proactive Contact Tracing
Figure 4 for Predicting Infectiousness for Proactive Contact Tracing

  Access Paper or Ask Questions

Double-Linear Thompson Sampling for Context-Attentive Bandits


Oct 15, 2020
Djallel Bouneffouf, Raphaël Féraud, Sohini Upadhyay, Yasaman Khazaeni, Irina Rish

Figure 1 for Double-Linear Thompson Sampling for Context-Attentive Bandits
Figure 2 for Double-Linear Thompson Sampling for Context-Attentive Bandits
Figure 3 for Double-Linear Thompson Sampling for Context-Attentive Bandits
* arXiv admin note: text overlap with arXiv:1906.09384 
  Access Paper or Ask Questions

Adversarial Feature Desensitization


Jun 08, 2020
Pouya Bashivan, Blake Richards, Irina Rish

Figure 1 for Adversarial Feature Desensitization
Figure 2 for Adversarial Feature Desensitization
Figure 3 for Adversarial Feature Desensitization
* submitted to Neurips 2020 
  Access Paper or Ask Questions

COVI White Paper


May 18, 2020
Hannah Alsdurf, Yoshua Bengio, Tristan Deleu, Prateek Gupta, Daphne Ippolito, Richard Janda, Max Jarvie, Tyler Kolody, Sekoul Krastev, Tegan Maharaj, Robert Obryk, Dan Pilat, Valerie Pisano, Benjamin Prud'homme, Meng Qu, Nasim Rahaman, Irina Rish, Jean-Franois Rousseau, Abhinav Sharma, Brooke Struck, Jian Tang, Martin Weiss, Yun William Yu

Figure 1 for COVI White Paper
* 63 pages, 1 figure 
  Access Paper or Ask Questions

Unified Models of Human Behavioral Agents in Bandits, Contextual Bandits and RL


May 12, 2020
Baihan Lin, Guillermo Cecchi, Djallel Bouneffouf, Jenna Reinen, Irina Rish

Figure 1 for Unified Models of Human Behavioral Agents in Bandits, Contextual Bandits and RL
Figure 2 for Unified Models of Human Behavioral Agents in Bandits, Contextual Bandits and RL
Figure 3 for Unified Models of Human Behavioral Agents in Bandits, Contextual Bandits and RL
Figure 4 for Unified Models of Human Behavioral Agents in Bandits, Contextual Bandits and RL
* This article supersedes and extends our work arXiv:1706.02897 (MAB) and arXiv:1906.11286 (RL) into the Contextual Bandit (CB) framework. It generalized extensively into multi-armed bandits, contextual bandits and RL settings to create a unified framework of human behavioral agents 
  Access Paper or Ask Questions

Towards Lifelong Self-Supervision For Unpaired Image-to-Image Translation


Mar 31, 2020
Victor Schmidt, Makesh Narsimhan Sreedhar, Mostafa ElAraby, Irina Rish

Figure 1 for Towards Lifelong Self-Supervision For Unpaired Image-to-Image Translation
Figure 2 for Towards Lifelong Self-Supervision For Unpaired Image-to-Image Translation
Figure 3 for Towards Lifelong Self-Supervision For Unpaired Image-to-Image Translation
Figure 4 for Towards Lifelong Self-Supervision For Unpaired Image-to-Image Translation

  Access Paper or Ask Questions

Online Fast Adaptation and Knowledge Accumulation: a New Approach to Continual Learning


Mar 12, 2020
Massimo Caccia, Pau Rodriguez, Oleksiy Ostapenko, Fabrice Normandin, Min Lin, Lucas Caccia, Issam Laradji, Irina Rish, Alexande Lacoste, David Vazquez, Laurent Charlin

Figure 1 for Online Fast Adaptation and Knowledge Accumulation: a New Approach to Continual Learning
Figure 2 for Online Fast Adaptation and Knowledge Accumulation: a New Approach to Continual Learning
Figure 3 for Online Fast Adaptation and Knowledge Accumulation: a New Approach to Continual Learning
Figure 4 for Online Fast Adaptation and Knowledge Accumulation: a New Approach to Continual Learning

  Access Paper or Ask Questions

Reinforcement Learning Models of Human Behavior: Reward Processing in Mental Disorders


Jun 28, 2019
Baihan Lin, Guillermo Cecchi, Djallel Bouneffouf, Jenna Reinen, Irina Rish

Figure 1 for Reinforcement Learning Models of Human Behavior: Reward Processing in Mental Disorders
Figure 2 for Reinforcement Learning Models of Human Behavior: Reward Processing in Mental Disorders
Figure 3 for Reinforcement Learning Models of Human Behavior: Reward Processing in Mental Disorders
Figure 4 for Reinforcement Learning Models of Human Behavior: Reward Processing in Mental Disorders
* arXiv admin note: substantial text overlap with arXiv:1706.02897 
  Access Paper or Ask Questions

Continual Learning with Self-Organizing Maps


Apr 19, 2019
Pouya Bashivan, Martin Schrimpf, Robert Ajemian, Irina Rish, Matthew Riemer, Yuhai Tu

Figure 1 for Continual Learning with Self-Organizing Maps
Figure 2 for Continual Learning with Self-Organizing Maps
Figure 3 for Continual Learning with Self-Organizing Maps
Figure 4 for Continual Learning with Self-Organizing Maps
* Continual Learning Workshop - NeurIPS 2018 
  Access Paper or Ask Questions

A Survey on Practical Applications of Multi-Armed and Contextual Bandits


Apr 02, 2019
Djallel Bouneffouf, Irina Rish

Figure 1 for A Survey on Practical Applications of Multi-Armed and Contextual Bandits
Figure 2 for A Survey on Practical Applications of Multi-Armed and Contextual Bandits
* under review by IJCAI 2019 Survey 
  Access Paper or Ask Questions

Kernelized Hashcode Representations for Biomedical Relation Extraction


Oct 31, 2018
Sahil Garg, Aram Galstyan, Greg Ver Steeg, Irina Rish, Guillermo Cecchi, Shuyang Gao

Figure 1 for Kernelized Hashcode Representations for Biomedical Relation Extraction
Figure 2 for Kernelized Hashcode Representations for Biomedical Relation Extraction
Figure 3 for Kernelized Hashcode Representations for Biomedical Relation Extraction
Figure 4 for Kernelized Hashcode Representations for Biomedical Relation Extraction
* To appear in the proceedings of conference, AAAI-19 
  Access Paper or Ask Questions

Learning to Learn without Forgetting By Maximizing Transfer and Minimizing Interference


Oct 29, 2018
Matthew Riemer, Ignacio Cases, Robert Ajemian, Miao Liu, Irina Rish, Yuhai Tu, Gerald Tesauro

Figure 1 for Learning to Learn without Forgetting By Maximizing Transfer and Minimizing Interference
Figure 2 for Learning to Learn without Forgetting By Maximizing Transfer and Minimizing Interference
Figure 3 for Learning to Learn without Forgetting By Maximizing Transfer and Minimizing Interference
Figure 4 for Learning to Learn without Forgetting By Maximizing Transfer and Minimizing Interference

  Access Paper or Ask Questions

Beyond Backprop: Online Alternating Minimization with Auxiliary Variables


Oct 24, 2018
Anna Choromanska, Sadhana Kumaravel, Ronny Luss, Irina Rish, Brian Kingsbury, Mattia Rigotti, Paolo DiAchille, Viatcheslav Gurev, Ravi Tejwani, Djallel Bouneffouf

Figure 1 for Beyond Backprop: Online Alternating Minimization with Auxiliary Variables
Figure 2 for Beyond Backprop: Online Alternating Minimization with Auxiliary Variables
Figure 3 for Beyond Backprop: Online Alternating Minimization with Auxiliary Variables
Figure 4 for Beyond Backprop: Online Alternating Minimization with Auxiliary Variables
* First four authors contributed equally to this work: A.C. - theory, manuscript, S.K. - code, experiments, R.L. - algorithm, experiments, I.R. - algorithm, manuscript 
  Access Paper or Ask Questions

Dialogue Modeling Via Hash Functions


Oct 18, 2018
Sahil Garg, Irina Rish, Guillermo Cecchi, Shuyang Gao, Palash Goyal, Sarik Ghazarian, Greg Ver Steeg, Aram Galstyan

Figure 1 for Dialogue Modeling Via Hash Functions
Figure 2 for Dialogue Modeling Via Hash Functions
* Presented at IJCAI-ICML 2018 Workshops. The paper is revised significantly with an addition of elaborate experimental analysis 
  Access Paper or Ask Questions

Learning Nonlinear Brain Dynamics: van der Pol Meets LSTM


May 24, 2018
German Abrevaya, Aleksandr Aravkin, Guillermo Cecchi, Irina Rish, Pablo Polosecki, Peng Zheng, Silvina Ponce Dawson

Figure 1 for Learning Nonlinear Brain Dynamics: van der Pol Meets LSTM
Figure 2 for Learning Nonlinear Brain Dynamics: van der Pol Meets LSTM
Figure 3 for Learning Nonlinear Brain Dynamics: van der Pol Meets LSTM
Figure 4 for Learning Nonlinear Brain Dynamics: van der Pol Meets LSTM
* 12 pages, 7 figures 
  Access Paper or Ask Questions

Adaptive Representation Selection in Contextual Bandit


May 15, 2018
Baihan Lin, Guillermo Cecchi, Djallel Bouneffouf, Irina Rish

Figure 1 for Adaptive Representation Selection in Contextual Bandit
Figure 2 for Adaptive Representation Selection in Contextual Bandit
Figure 3 for Adaptive Representation Selection in Contextual Bandit
Figure 4 for Adaptive Representation Selection in Contextual Bandit

  Access Paper or Ask Questions

Learning Neural Markers of Schizophrenia Disorder Using Recurrent Neural Networks


Dec 01, 2017
Jumana Dakka, Pouya Bashivan, Mina Gheiratmand, Irina Rish, Shantenu Jha, Russell Greiner

Figure 1 for Learning Neural Markers of Schizophrenia Disorder Using Recurrent Neural Networks
Figure 2 for Learning Neural Markers of Schizophrenia Disorder Using Recurrent Neural Networks
* To be published as a workshop paper at NIPS 2017 Machine Learning for Health (ML4H) 
  Access Paper or Ask Questions

Context Attentive Bandits: Contextual Bandit with Restricted Context


Jun 07, 2017
Djallel Bouneffouf, Irina Rish, Guillermo A. Cecchi, Raphael Feraud

Figure 1 for Context Attentive Bandits: Contextual Bandit with Restricted Context
Figure 2 for Context Attentive Bandits: Contextual Bandit with Restricted Context
Figure 3 for Context Attentive Bandits: Contextual Bandit with Restricted Context
Figure 4 for Context Attentive Bandits: Contextual Bandit with Restricted Context
* IJCAI 2017 
  Access Paper or Ask Questions