Publications
2024
Journals
Adam Ibrahim, Benjamin Thérien, Kshitij Gupta, Mats L. Richter, Quentin Anthony, Timothée Lesort, Eugene Belilovsky, Irina Rish, "Simple and Scalable Strategies to Continually Pre-train Large Language Models", Transactions on Machine Learning Research (TMLR), 2024.
Germán Abrevaya, Mahta Ramezanian-Panahi, Jean-Christophe Gagnon-Audet, Pablo Polosecki, Irina Rish, Silvina Ponce Dawson, Guillermo Cecchi, Guillaume Dumas, "Effective Latent Differential Equation Models via Attention and Multiple Shooting". In Transactions on Machine Learning Research (TMLR), 2024.
Mohammad-Javad Darvishi-Bayazi, Mohammad Sajjad Ghaemi, Timothee Lesort, Md Rifat Arefin, Jocelyn Faubert, Irina Rish, “Amplifying Pathological Detection in EEG Signaling Pathways through Cross-Dataset Transfer Learning”, Computers in Biology and Medicine, Vol 169, February 2024.
Conferences:
Alessio Mora, Irene Tenison, Paolo Bellavista, Irina Rish. "Knowledge distillation for federated learning: a practical guide." Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, Survey Track. pp 8188-8196.
Rifat Arefin, Yan Zhang, Aristide Baratin, Francesco Locatello, Irina Rish, Dianbo Liu, and Kenji Kawaguchi. "Unsupervised Concept Discovery Mitigates Spurious Correlations". In Proc of ICML 2024. arXiv preprint arXiv:2402.13368 (2024).
Mohammad Reza Samsami*, Artem Zholus*, Janarthanan Rajendran, and Sarath Chandar. "Mastering Memory Tasks with World Models." The Twelfth International Conference on Learning Representations (ICLR), 2024 (top-1.2%).
Arjun Ashok, Étienne Marcotte, Valentina Zantedeschi, Nicolas Chapados, and Alexandre Drouin. "TACTiS-2: Better, Faster, Simpler Attentional Copulas for Multivariate Time Series." The Twelfth International Conference on Learning Representations (ICLR), 2024.
Amin Mansouri, Jason Hartford, Yan Zhang, Yoshua Bengio. "Object-centric architectures enable efficient causal representation learning" The Twelfth International Conference on Learning Representations (ICLR), 2024.
Kartik Ahuja*, Amin Mansouri*, Yixin Wang, "Multi-Domain Causal Representation Learning via Weak Distributional Invariances", AISTATS 2024
Megh Thakkar, Quentin Fournier, Matthew Riemer, Pin-Yu Chen, Amal Zouaq, Payel Das, Sarath Chandar, "A Deep Dive into the Trade-Offs of Parameter-Efficient Preference Alignment Techniques", ACL 2024.
Mohammad-Javad Darvishi-Bayazi, Mohammad Sajjad Ghaemi, Timothee Lesort, Md Rifat Arefin, Jocelyn Faubert, Irina Rish, “Amplifying Pathological Detection in EEG Signaling Pathways through Cross-Dataset Transfer Learning”, in CoLLAs 2024 - Journal Track.
Workshops:
Mohammad-Javad Darvishi-Bayazi, Md Rifat Arefin, Jocelyn Faubert, Irina Rish, “VFA: Vision Frequency Analysis of Foundation Models and Human”, In ICML 2024 Workshop on Foundation Models in the Wild.
Arnav Kumar Jain, Harley Wiltzer, Jesse Farebrother, Irina Rish, Glen Berseth, Sanjiban Choudhury, "Revisiting Successor Features for Inverse Reinforcement Learning". In ICML 2024 Workshop on Model of Human Feedback for AI Alignment.
Notsawo Jr, Pascal, Hattie Zhou, Mohammad Pezeshki, Irina Rish, and Guillaume Dumas. "Predicting Grokking Long Before it Happens: A look into the loss landscape of models which grok". In the ICLR 2024 Workshop on Mathematical and Empirical Understanding of Foundation Models (ME-FoMo).
Justine Gehring*, Nizar Islah*, Diganta Misra*, Massimo Caccia, Irina Rish. "GitChameleon: Breaking the version barrier for code generation models". In Proc of the 4th DMLR workshop at ICLR 2024
Karolis Jucys*, George Adamopoulos*, Mehrab Hamidi, Stephanie Milani, Mohammad Reza Samsami, Artem Zholus, Sonia Joseph, Blake Richards, Irina Rish, and Ozgur Simsek. "Interpretability in Action: Exploratory Analysis of VPT, a Minecraft Agent". In the ICML 2024 Workshop on Mechanistic Interpretability.
Matthew Riemer*, Gopeshh Subbaraj*, Glen Berseth, Irina Rish. "Realtime Reinforcement Learning: Towards Rapid Asynchronous Deployment of Large Models". In the ICML 2024 Workshop on Aligning Reinforcement Learning Experimentalists and Theorists and the RLC 2024 Workshop on Finding the Frame.
Maximilian Puelma Touzel, Amin Memarian, Matthew D Riemer, Andrei Mircea, Andrew Robert Williams, Elin Ahlstrand, Lucas Lehnert, Rupali Bhati, Guillaume Dumas, Irina Rish. "Scalable Approaches for a Theory of Many Minds". ICML 2024 Workshop on Agentic Markets.
Ivan Anokhin, Rishav, Stephen Chung, Irina Rish, Samira Ebrahimi Kahou. "Handling Delay in Reinforcement Learning Caused by Parallel Computations of Neurons". In the ICML 2024 Workshop on Aligning Reinforcement Learning Experimentalists and Theorists and the RLC 2024 Workshop on Deployable RL.
Andrei Mircea, Ekaterina Lobacheva, Irina Rish. "Gradient Dissent in Language Model Training and Saturation" In High-dimensional Learning Dynamics 2024: The Emergence of Structure and Reasoning.
Amin Memarian, Touraj Laleh, Irina Rish, Ardavan S. Nobandegani. "Is a Good Description Worth a Thousand Pictures? Reducing Multimodal Alignment to Text-Based, Unimodal Alignment" In the ICML 2024 Workshop on Humans, Algorithmic Decision-Making and Society: Modeling Interactions and Impact & the ICML 2024 Workshop on Models of Human Feedback for AI Alignment.
Rishika Bhagwatkar, Shravan Nayak, Reza Bayat, Alexis Roger, Daniel Z Kaplan, Pouya Bashivan, Irina Rish. "Towards Adversarially Robust Vision-Language Models: Insights from Design Choices and Prompt Formatting Techniques". In the ICML 2024 Workshop on the Next Generation of AI Safety and ICML 2024 Workshop on Trustworthy Multi-modal Foundation Models and AI Agents (TiFA).
Ayush Kaushal*, Tejas Vaidhya*, Tejas Pandey*, Aaryan Bhagat, Irina Rish. "TriLM vs FloatLM: Ternary LLMs are more Performant than Quantized FP16 LLMs". In the ICML 2024 Workshop on Foundation Models in the Wild. Extended version: Spectra: A Comprehensive Study of Ternary, Quantized, and FP16 Language Models.
Ayush Kaushal*, Tejas Vaidhya*, Irina Rish. "LoRD: Low-Rank Decomposition of Monolingual Code LLMs for One-Shot Compression". In the ICML 2024 Workshop on Foundation Models in the Wild.
Ivan Anokhin, Rishav, Stephen Chung, Irina Rish, Samira Ebrahimi Kahou. "Handling Delay in Reinforcement Learning Caused by Parallel Computations of Neurons". In the ICML 2024 Workshop on Aligning Reinforcement Learning Experimentalists and Theorists and the RLC 2024 Workshop on Deployable RL.
Tommaso Tosato, Pascal Jr Tikeng Notsawo, Saskia Helbling, Irina Rish, Guillaume Dumas. "Lost in Translation: The Algorithmic Gap Between LMs and the Brain". In the ICML 2024 Workshop on LLMs and Cognition .
2023
Journals
Mohammad-Javad Darvishi-Bayazi, Andrew Law, Sergio Mejia Romero, Sion Jennings, Irina Rish, Jocelyn Faubert. "Beyond performance: the role of task demand, effort, and individual differences in ab initio pilots". In Nature Sci Rep 13, 14035 (2023).
Mohammad-Javad Darvishi-Bayazi, Andrew Law, Sergio Mejia Romero, Sion Jennings, Irina Rish, and Jocelyn Faubert. "Neural efficiency in an aviation task with different levels of difficulty: Assessing different biometrics during a performance task." Journal of Vision 23, no. 9 (2023): 5647-5647.
Irene Tenison, Sai Aravind Sreeramadas, Vaikkunth Mugunthan, Edouard Oyallon, Irina Rish, Eugene Belilovsky. "Gradient Masked Averaging for Federated Learning". In Transactions on Machine Learning Research (2023).
Gagnon-Audet, Jean-Christophe, Kartik Ahuja, Mohammad-Javad Darvishi-Bayazi, Guillaume Dumas, and Irina Rish. "WOODS: Benchmarks for Out-of-Distribution Generalization in Time Series Tasks" In Transactions on Machine Learning Research (2023). arXiv preprint arXiv:2203.09978 & ICLR2024.
Lam, Guillaume, Irina Rish, and Philippe C. Dixon. "Estimating individual minimum calibration for deep-learning with predictive performance recovery: An example case of gait surface classification from wearable sensor gait data." Journal of Biomechanics (2023): 111606.
Aarohi Srivastava, et al ( Diganta Misra is among the co-authors) “Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models”, Transactions on Machine Learning Research (TMLR), 2023.
Conferences
Ardavan S Nobandegani, Irina Rish, Thomas Shultz, "Decision-Making Paradoxes in Humans vs Machines: The case of the Allais and Ellsberg Paradoxes", The 45th Annual Conference of the Cognitive Science Society (CogSci), 2023.
Ardavan S. Nobandegani, Thomas R. Shultz. "Neural Network Modeling of Pure Reasoning in Preverbal Infants". The 45th Annual Conference of the Cognitive Science Society (CogSci), 2023.
Thomas R. Shultz, Ardavan S. Nobandegani, Zilong Wang. "A Neural Model of Number Comparison with Robust Generalization". The 45th Annual Conference of the Cognitive Science Society (CogSci), 2023.
Ardavan S. Nobandegani, Irina Rish, Thomas R. Shultz. "AI Agents Learn to Trust". [Abstract]. The 45th Annual Conference of the Cognitive Science Society (CogSci), 2023. (poster presentation) arXiv preprint arXiv:2312.12868.
Arnav Kumar Jain, Lucas Lehnert, Irina Rish and Glen Berseth, "Maximum State Entropy Exploration using Predecessor and Successor Representations", in Proc of NeurIPS 2023.
Bouneffouf, Djallel, Mayank Agarwal, and Irina Rish. "Dialogue System with Missing Observation." ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2023.
Timothée Lesort, Oleksiy Ostapenko, Diganta Misra, Md Rifat Arefin, Pau Rodríguez, Laurent Charlin, Irina Rish (2023). "Challenging Common Assumptions about Catastrophic Forgetting." Second Conference on Lifelong Learning Agents (CoLLAs 2023)
Caballero, Ethan; Gupta, Kshitij; Rish, Irina; Krueger, David (2022). “Broken Neural Scaling Laws”. International Conference on Learning Representations (ICLR 2023).
S Nath, GR Subbaraj, K Khetarpal, SE Kahou, "Discovering Object-Centric Generalized Value Functions From Pixels", Proceedings of the International Conference on Machine Learning (ICML), PMLR 202, 2023.
Trang Nguyen, Amin Mansouri, Kanika Madan, Nguyen Duy Khuong, Kartik Ahuja, Dianbo Liu, Yoshua Bengio, "Reusable Slotwise Mechanisms" NeurIPS 2023.
Workshops
Alexis Roger, Esma Aimeur, Irina Rish, "Towards Ethical Multimodal Systems", in the First Workshop on AI meets Moral Philosophy and Moral Psychology (MP2) at NeurIPS 2023.
Sonia Joseph*, Artem Zholus*, Mohammad Reza Samsami*, Blake A. Richards, "Mining the Diamond Miner: Mechanistic Interpretability on the Video PreTraining Agent", in the 1st Workshop on Attributing Model Behavior at Scale (ATTRIB) at NeurIPS 2023.
Kshitij Gupta, Benjamin Therien, Adam Ibrahim, Mats Leon Richter, Quentin Anthony, Eugene Belilovsky, Irina Rish, Timothee Lesort, "Continual Pre-Training of Large Language Models: How to (re)warm your model?" (new version), in Efficient Natural Language and Speech Processing (ENLSP-III) workshop at NeurIPS 2023.
Kashif Rasul, Arjun Ashok, Andrew Robert Williams, Arian Khorasani, George Adamopoulos, Rishika Bhagwatkar, Marin Biloš, Hena Ghonia, Nadhir Hassen, Anderson Schneider, Sahil Garg, Alexandre Drouin, Nicolas Chapados, Yuriy Nevmyvaka, Irina Rish, "Lag-Llama: Towards Foundation Models for Time Series Forecasting", in R0-FoMo: Robustness of Few-shot and Zero-shot Learning in Large Foundation Models workshop at NeurIPS 2023. Extended version.
Nizar Islah, Diganta Misra, Timothy Nest, Matthew D Riemer, Irina Rish, Eilif Benjamin Muller, "Mitigating Mode Collapse in Sparse Mixture of Experts", in New in Machine Learning Workshop at NeurIPS 2023.
Germán Abrevaya, Mahta Ramezanian-Panahi, Jean-Christophe Gagnon-Audet, Pablo Polosecki, Irina Rish, Silvina Ponce Dawson, Guillermo Cecchi, Guillaume Dumas, "Effective Latent Differential Equation Models via Attention and Multiple Shooting". The Symbiosis of Deep Learning and Differential Equations III workshop at NeurIPS 2023.
Kshitij Gupta, Benjamin Therien, Adam Ibrahim, Mats Leon Richter, Quentin Anthony, Eugene Belilovsky, Irina Rish, Timothee Lesort. "Continual Pre-Training of Large Language Models: How to re-warm your model?". In ES-FoMo: Efficient Systems for Foundation Models workshop at ICML-2023 (2023).
Ardavan S. Nobandegani, Thomas R. Shultz, and Irina Rish. "Cognitive Models as Simulators: Using Cognitive Models to Tap into Implicit Human Feedback" In Interactive Learning with Implicit Human Feedback (ILHF) workshop at ICML-2023 (2023).
Jain, Arnav Kumar, Lucas Lehnert, Irina Rish, and Glen Berseth. "Maximum State Entropy Exploration using Predecessor and Successor Representations" In New Frontiers in Learning, Control, and Dynamical Systems workshop at the International Conference on Machine Learning (ICML-2023). arXiv preprint arXiv:2306.14808 (2023).
Alex Gu, Bharat Runwal, Diganta Misra, Ria Sonecha, Saaketh Vedantam. "Pruning CodeBERT for Improved Code-to-Text Efficiency" In Sparsity in Neural Networks (SNN) workshop, ICLR 2023.
Kartik Ahuja, Amin Mansouri, Yixin Wang, "Multi-Domain Causal Representation Learning via Weak Distributional Invariances", NeurIPS 2023 Workshop on Causal Representation Learning.
Amin Mansouri, Jason Hartford, Yan Zhang, Yoshua Bengio. "Object centric architectures enable efficient causal representation learning" NeurIPS 2023 Workshop on Causal Representation Learning.
2022
Journals
Khetarpal, Khimya, Matthew Riemer, Irina Rish, and Doina Precup. "Towards Continual Reinforcement Learning: A Review and Perspectives" Journal of Artificial Intelligence Research 75 (2022): 1401-1476.
Ramezanian-Panahi, Mahta, Germán Abrevaya, Jean-Christophe Gagnon-Audet, Vikram Voleti, Irina Rish, and Guillaume Dumas. "Generative Models of Brain Dynamics." Frontiers in Artificial Intelligence (2022): 147. June 2022.
Conferences:
JC Layoun, A Roger, I Rish. Aligning MAGMA by Few-Shot Learning and Finetuning. Presented at Montreal AI Symposium 2022 conference. arXiv:2210.14161, 2022.
Ardavan S. Nobandegani, Thomas Shultz, and Irina Rish. “Cognitive Models as Simulators: The Case of Moral Decision-Making”. In J. Culbertson, A. Perfors, H. Rabagliati & V. Ramenzoni (Eds.), Proceedings of the 44th Annual Conference of the Cognitive Science Society. https://arxiv.org/abs/2210.04121 (2022).
Riemer, Matthew, Sharath Chandra Raparthy, Ignacio Cases, Gopeshh Subbaraj, Maximilian Puelma Touzel, and Irina Rish. "Continual learning in environments with polynomial mixing times" Advances in Neural Information Processing Systems 35 (2022): 21961-21973.
Ernoult, Maxence M., Fabrice Normandin, Abhinav Moudgil, Sean Spinney, Eugene Belilovsky, Irina Rish, Blake Richards, and Yoshua Bengio. "Towards Scaling Difference Target Propagation by Learning Backprop Targets". In International Conference on Machine Learning (ICML), pp. 5968-5987. July 2022.
Ostapenko, Oleksiy, Timothee Lesort, Pau Rodríguez, Md Rifat Arefin, Arthur Douillard, Irina Rish, and Laurent Charlin. "Foundational Models for Continual Learning: An Empirical Study of Latent Replay " arXiv preprint arXiv:2205.00329 (2022). 1st CoLLAs conference, August 2022.
Gauthier, Shanel, Benjamin Thérien, Laurent Alsène-Racicot, Muawiz Chaudhary, Irina Rish, Eugene Belilovsky, Michael Eickenberg, and Guy Wolf. "Parametric Scattering Networks" In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5749-5758.June 2022.
Gagnon-Audet, Jean-Christophe, Soroosh Shahtalebi, Frank Rudzicz, and Irina Rish. "A Remedy For Distributional Shifts Through Expected Domain Translation.". In ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4523-4527. IEEE, May 2022.
Mittal, Sarthak, Sharath Chandra Raparthy, Irina Rish, Yoshua Bengio, and Guillaume Lajoie. "Compositional Attention: Disentangling Search and Retrieval" arXiv preprint arXiv:2110.09419, ICLR, 2022.
Kartik Ahuja, Jason Hartford, Yoshua Bengio. “Properties from Mechanisms: An Equivariance Perspective on Identifiable Representation Learning”, In Proc of ICLR, 2022.
Kartik Ahuja, Divyat Mahajan, Vasilis Syrgkanis, Ioannis Mitliagkas, “Towards Efficient Representation Identification in Supervised Learning”, In Proc of CLeaR, 2022.
Abhin Shah, Karthikeyan Shanmugam, Kartik Ahuja. “Finding Valid Adjustments under Non-Ignorability with Minimal DAG Knowledge”, AISTATS, 2022.
Workshops:
A Raj, Irene Tenison, Kacem Khalid, Felipe Magalahes, Gabriela Nicolescu. "FedSHIBU: Federated similarity based head independent body update" In Federated Learning: Recent advances and new Challenges Workshop, NeurIPS 2022.
Ibrahim, Adam; Guille-Escuret, Charles; Mitliagkas, Ioannis; Rish, Irina; Krueger, David; Bashivan, Pouya. "Towards Out-of-Distribution Adversarial Robustness", In New Frontiers in Adversarial Machine Learning workshop at ICML-2022, July 2022.
Lesort, Timothée, Oleksiy Ostapenko, Diganta Misra, Md Rifat Arefin, Pau Rodríguez, Laurent Charlin, and Irina Rish. "Scaling the Number of Tasks in Continual Learning" arXiv preprint arXiv:2207.04543, CoLLAs workshop (2022).
Amin Mansouri, Jason Hartford, Kartik Ahuja, Yoshua Bengio. "Object-Centric Causal Representation Learning" NeurIPS 2022 workshop on Symmetry and Geometry in Neural Representations.
Maximilian Puelma Touzel and Erick Lachapelle. "Topic correlation networks inferred from open-ended survey responses reveal structural signatures of ideology behind carbon tax opinion". NeurIPS 2022 Workshop on Tackling Climate Change with Machine Learning.
Diganta Misra, Bharat Runwal, Tianlong Chen, Zhangyang Wang, and Irina Rish. "APP: Anytime Progressive Pruning" arXiv preprint arXiv:2204.01640 (2022). In 1st Workshop on Dynamic Neural Networks, ICML 2022 (DyNN) and 2nd Sparsity in Neural Networks workshop 2022 (SNN), July 2022.
Memarian, Amin, Maximilian Puelma Touzel, Matthew D. Riemer, Rupali Bhati, and Irina Rish. "Summarizing Societies: Agent Abstraction in Multi-Agent Reinforcement Learning" From Cells to Societies: Collective Learning across Scales. ICLR workshop, April 2022.
Nadhir Hassen, Irina Rish. "Approximate Bayesian Optimisation for Neural Networks", in AAAI-22 Workshop on Learning Network Architecture During Training, 2022.
2021
Journals
Abrevaya, Germán, Guillaume Dumas, Aleksandr Y Aravkin, Peng Zheng, Jean-Christophe Gagnon-Audet, James Kozloski, Pablo Polosecki, Guillaume Lajoie, David Cox, Silvina Ponce Dawson, Guillermo Cecchi, Irina Rish. "Learning Brain Dynamics With Coupled Low-Dimensional Nonlinear Oscillators and Deep Recurrent Networks", Neural Computation 33, no. 8 (2021): 2087-2127.
S Shahtalebi, SF Atashzar, RV Patel, MS Jog, A Mohammadi. "A deep explainable artificial intelligent framework for neurological disorders discrimination", Scientific reports 11 (1), 9630.
Conferences
Ahuja, Kartik, Ethan Caballero, Dinghuai Zhang, Jean-Christophe Gagnon-Audet, Yoshua Bengio, Ioannis Mitliagkas, and Irina Rish. "Invariance Principle Meets Information Bottleneck for Out-of-Distribution Generalization." Advances in Neural Information Processing Systems (NeurIPS) 34 (2021): 3438-3450.
Bashivan, Pouya, Reza Bayat, Adam Ibrahim, Kartik Ahuja, Mojtaba Faramarzi, Touraj Laleh, Blake Richards, and Irina Rish. "Adversarial Feature Desensitization" Advances in Neural Information Processing Systems (NeurIPS) 34 (2021): 10665-10677.
Bouneffouf, Djallel, Raphael Feraud, Sohini Upadhyay, Mayank Agarwal, Yasaman Khazaeni, and Irina Rish. "Toward Skills Dialog Orchestration with Online Learning" In ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 3600-3604. IEEE, 2021.
Bouneffouf, Djallel, Raphaël Féraud, Sohini Upadhyay, Yasaman Khazaeni, and Irina Rish. "Double-Linear Thompson Sampling for Context-Attentive Bandits." In ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 3450-3454. IEEE, 2021.
Bengio Y; Gupta P; Maharaj, T; Rahaman, N; Weiss, M; Deleu, T; Muller E.B; Qu, M; Schmidt, V; St-charles, P.L; Alsdurf, H; Bilaniuk, O; Buckeridge, D; Caron G; Carrier, P.L; Ghosn, J; Ortiz Gagne, S; Pal, C; Rish, I; Schölkopf, B; Sharma, A; Tang, J; Williams, A. Predicting Infectiousness for Proactive Contact Tracing. 2021. International Conference on Learning Representations (ICLR).
Shanel Gauthier, Benjamin Thérien, Laurent Alsène-Racicot, Irina Rish, Eugene Belilovsky, Michael Eickenberg, Guy Wolf. "Parametric Scattering Networks", in Proc of 2021 Conference on the Mathematical Theory of Deep Learning (DeepMath 2021).
Dinghuai Zhang, Kartik Ahuja, Yilun Xu, Yisen Wang, Aaron Courville. “Can Subnetwork Structure be the Key to Out-of-Distribution Generalization?” In Proc of ICML 2021.
Kartik Ahuja, P. Sattigeri, K. Shanmugam, D. Wei, K.N. Ramamurthy, M. Kocaglu. “Conditionally Independent Data Generation.” In Proc of UAI 2021.
Kartik Ahuja, Jun Wang, Amit Dhurandhar, Karthikeyan Shanmugam, Kush R. Varshney. “Empirical or Invariant Risk Minimization? A Sample Complexity Perspective.” In Proc of ICLR 2021.
Kartik Ahuja, Karthikeyan Shanmugam, Amit Dhurandhar, “Linear Regression Games: Convergence Guarantees to Approximate Out-of-Distribution Solutions”. In Proc of AISTATS, 2021.
Workshops:
Normandin, Fabrice, 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. "Sequoia: A Software Framework to Unify Continual Learning Research", arXiv preprint arXiv:2108.01005 (2021). Workshop on Theory and Foundation of Continual Learning (ICML Workshop), 2021.
Tenison, Irene, Sreya Francis, and Irina Rish. "Gradient Masked Federated Optimization" arXiv preprint arXiv:2104.10322 (2021). ICLR 2021 workshop on Distributed and Private Machine Learning (DPML) and NeurIPS 2021 Workshop on Federated Learning.
Francis, Sreya, Irene Tenison, and Irina Rish. "Towards Causal Federated Learning For Enhanced Robustness and Privacy" arXiv preprint arXiv:2104.06557 (2021). ICLR 2021 workshop on Distributed and Private Machine Learning (DPML), 2021
Lesort, Timothée, Thomas George, and Irina Rish. "Continual Learning in Deep Networks: an Analysis of the Last Layer" arXiv preprint arXiv:2106.01834 (2021).. International Conference of Machine Learning 2021 (ICML) Workshop on Theory and Foundation of Continual Learning.
Lesort, Timothée, Massimo Caccia, and Irina Rish. "Understanding Continual Learning Settings with Data Distribution Drift Analysis". arXiv preprint arXiv:2104.01678 (2021). International Conference of Machine Learning 2021 (ICML) Workshop on Theory and Foundation of Continual Learning.
Shahtalebi, Soroosh, Jean-Christophe Gagnon-Audet, Touraj Laleh, Mojtaba Faramarzi, Kartik Ahuja, and Irina Rish. "SAND-mask: An Enhanced Gradient Masking Strategy for the Discovery of Invariances in Domain Generalization" arXiv preprint arXiv:2106.02266 (2021). ICML 2021 workshop on Uncertainty and Robustness in ML.
Gabriele Prato, Simon Guiroy, Ethan Caballero, Irina Rish and Sarath Chandar. “Scaling Laws for the Few-Shot Adaptation of Pre-trained Image Classifiers“, in Proc of ICML 2021 Workshop on Uncertainty & Robustness in Deep Learning.
Amin Mansouri, Sean Spinney, Amin Memarian, Patricia Conrod, and Irina Rish. "Identifying Invariant and Sparse Predictors in High-dimensional Data:", in Proc of ICML 2021 Workshop on Uncertainty & Robustness in Deep Learning.
Lin, Baihan, Guillermo Cecchi, Djallel Bouneffouf, Jenna Reinen, and Irina Rish. "Models of Human Behavioral Agents in Bandits, Contextual Bandits and RL" In International Workshop on Human Brain and Artificial Intelligence, pp. 14-33. Springer, Singapore, 2021.
2020
Journals
Polosecki, P; Castro, E; Rish, I; Pustina, D; Warner J.H; Wood, A; Sampaio, C; Cecchi, G. Resting-state connectivity stratifies premanifest Huntington’s disease by longitudinal cognitive decline rate. 2020. Nature Scientific Reports 10 (1), 1-15.
Conferences
Garg, S; Rish, I; Cecchi G; Goyal, P; Ghazarian, S; Gao, S; Ver Steeg, G; Galstyan, A. "Modeling Psychotherapy Dialogues with Kernelized Hashcode Representations: A Nonparametric Information-Theoretic Approach", 2020. Association for the Advancement of Artificial Intelligence (AAAI).
Lin, B; Cecchi, G; Bouneffouf, D; Reinen, J; Rish, I. "A Story of Two Streams: Reinforcement Learning Models from Human Behavior and Neuropsychiatry". 2020. Autonomous Agents & Multiagent Systems (AAMAS).
Caccia, M; Rodriguez, P; Ostapenko, O; Normandin, F; Lin, M; Caccia, L; Laradji, I.H; Rish, I; Lacoste, A; Vazquez, D; Charlin L. "Online Fast Adaptation and Knowledge Accumulation: A New Approach to Continual Learning". 2020. NeurIPS.
Bouneffouf, D; Rish, I; Aggarwal, C. Survey on Applications of Multi-Armed and Contextual Bandits. 2020. IEEE Congress on Evolutionary Computation (CEC).
Workshops:
Touraj L; Raparthy C.S; Rish, I. Chaotic Continual Learning. 2020. International Conference on Machine Learning (ICML) Workshop on Lifelong Learning.
Lin, B; Cecchi, G; Bouneffouf, D; Reinen, J; Rish, I."Unified Models of Human Behavioral Agents in Bandits, Contextual Bandits and RL" , Knowledge Discovery and Data Mining (KDD) Workshop on Designing AI in support of Good Mental Health. 2020.
Research Reports
Germán Abrevaya, Mahta Ramezanian-Panahi, Jean-Christophe Gagnon-Audet, Irina Rish, Pablo Polosecki, Silvina Ponce Dawson, Guillermo Cecchi, Guillaume Dumas. "
GOKU-UI: Ubiquitous Inference through Attention and Multiple Shooting for Continuous-time Generative Models." arXiv preprint arXiv:2307.05735 (2023).
Towards ethical multimodal systems
Roger, Alexis, Esma Aïmeur, and Irina Rish. "Towards ethical multimodal systems." arXiv preprint arXiv:2304.13765 (2023).
A survey on compositional generalization in applications
Lin, Baihan, Djallel Bouneffouf, and Irina Rish. "A survey on compositional generalization in applications." arXiv preprint arXiv:2302.01067 (2023).
Knowledge distillation for federated learning: a practical guide
Mora, Alessio, Irene Tenison, Paolo Bellavista, and Irina Rish. "Knowledge distillation for federated learning: a practical guide." arXiv preprint arXiv:2211.04742 (2022).
Gradient Masked Averaging for Federated Learning
Tenison, Irene, Sai Aravind Sreeramadas, Vaikkunth Mugunthan, Edouard Oyallon, Eugene Belilovsky, and Irina Rish. "Gradient Masked Averaging for Federated Learning." arXiv preprint arXiv:2201.11986 (2022).
Scaling Laws for the Few-Shot Adaptation of Pre-trained Image Classifiers
Prato, Gabriele, Simon Guiroy, Ethan Caballero, Irina Rish, and Sarath Chandar. "Scaling Laws for the Few-Shot Adaptation of Pre-trained Image Classifiers." arXiv preprint arXiv:2110.06990 (2021). (slides)
Gupta, P; Maharaj, T; Weiss, M; Rahaman, N; Alsdurf, H; Sharma A; Minoyan, N; Harnois-Leblanc, S; Schmidt, V; St. Charles, P.L; Deleu, T; Williams, A; Patel, A; Qu, M; Bilaniuk, O; Marceau Caron, G; Carrier, P.L; Ortiz-Gagné, S; Rousseau, M.A; Buckeridge D; Ghosn, J; Zhang, Y; Schölkopf, B; Tang, J; Rish, I; Pal, C; Merckx, J; Muller, E.B; Bengio, Y. COVI-AgentSim: An Agent-based Model for Evaluating Methods of Digital Contact Tracing. 2021. https://arxiv.org/abs/2010.16004
Bashivan, P; Bayat, R; Ibrahim, A; Ahuja, K; Faramarzi, M; Laleh, T, Richards, B; Rish, I. Adversarial Feature Desensitization. 2021. https://arxiv.org/abs/2006.04621
Khetarpal, K; Riemer, M; Rish, I; Precup, D. Towards Continual Reinforcement Learning: A Review and Perspectives. 2021. https://arxiv.org/abs/2012.13490
Alsdurf, H; Belliveau, E ; Bengio, Y; Deleu, T; Gupta, P; Ippolito, D; Janda, R; Jarvie, M; Kolody T; Krastev, S; Maharaj, T; Obryk, R; Pilat, D; Pisano V, Prud'homme, B; Qu M; Rahaman N; Rish, I; Rousseau, J.F; Sharma, A; Struck B; Tang, J; Weiss, M; Yu, Y.W. COVI White Paper. 2020. https://arxiv.org/abs/2005.08502
Schmidt, V; Sreedhar, M.N, ElAraby, M; Rish I. 2020. Towards Lifelong Self-Supervision For Unpaired Image-to-Image Translation. https://arxiv.org/abs/2004.00161
For publications by Irina Rish prior to 2019 see this page.