Nicolas Le Roux

93 papers A* 20A 9B 3Journal 45Unranked 13

Year	Rank	Type	Title / Venue / Authors
2025	A	`conf`	Fast Convergence of Softmax Policy Mirror Ascent. AISTATS Reza Asad, Reza Babanezhad Harikandeh, Issam H. Laradji, Nicolas Le Roux, Sharan Vaswani
2025	J	`jnl`	Tapered Off-Policy REINFORCE: Stable and efficient reinforcement learning for LLMs. CoRR Nicolas Le Roux, Marc G. Bellemare, Jonathan Lebensold, Arnaud Bergeron, Joshua Greaves, Alexandre Fréchette, Carolyne Pelletier, Eric Thibodeau-Laufer, Sándor Tóth, Sam Work
2025	A*	`conf`	VinePPO: Refining Credit Assignment in RL Training of LLMs. ICML Amirhossein Kazemnejad, Milad Aghajohari, Eva Portelance, Alessandro Sordoni, Siva Reddy, Aaron C. Courville, Nicolas Le Roux
2025	A*	`conf`	fLSA: Learning Semantic Structures in Document Collections Using Foundation Models. EMNLP Weijia Xu, Nebojsa Jojic, Nicolas Le Roux
2024	J	`jnl`	Fast Convergence of Softmax Policy Mirror Ascent. CoRR Reza Asad, Reza Babanezhad, Issam H. Laradji, Nicolas Le Roux, Sharan Vaswani
2024	A*	`conf`	Improving Context-Aware Preference Modeling for Language Models. NeurIPS Silviu Pitis, Ziang Xiao, Nicolas Le Roux, Alessandro Sordoni
2024	J	`jnl`	Improving Context-Aware Preference Modeling for Language Models. CoRR Silviu Pitis, Ziang Xiao, Nicolas Le Roux, Alessandro Sordoni
2024	A*	`conf`	Language-guided Skill Learning with Temporal Variational Inference. ICML Haotian Fu, Pratyusha Sharma, Elias Stengel-Eskin, George Konidaris, Nicolas Le Roux, Marc-Alexandre Côté, Xingdi Yuan
2024	J	`jnl`	Language-guided Skill Learning with Temporal Variational Inference. CoRR Haotian Fu, Pratyusha Sharma, Elias Stengel-Eskin, George Konidaris, Nicolas Le Roux, Marc-Alexandre Côté, Xingdi Yuan
2024	A*	`conf`	Towards Modular LLMs by Building and Reusing a Library of LoRAs. ICML Oleksiy Ostapenko, Zhan Su, Edoardo M. Ponti, Laurent Charlin, Nicolas Le Roux, Lucas Caccia, Alessandro Sordoni
2024	J	`jnl`	Towards Modular LLMs by Building and Reusing a Library of LoRAs. CoRR Oleksiy Ostapenko, Zhan Su, Edoardo Maria Ponti, Laurent Charlin, Nicolas Le Roux, Matheus Pereira, Lucas Caccia, Alessandro Sordoni
2024	J	`jnl`	VinePPO: Unlocking RL Potential For LLM Reasoning Through Refined Credit Assignment. CoRR Amirhossein Kazemnejad, Milad Aghajohari, Eva Portelance, Alessandro Sordoni, Siva Reddy, Aaron C. Courville, Nicolas Le Roux
2024	J	`jnl`	fPLSA: Learning Semantic Structures in Document Collections Using Foundation Models. CoRR Weijia Xu, Nebojsa Jojic, Nicolas Le Roux
2023	A*	`conf`	Decision-Aware Actor-Critic with Function Approximation and Theoretical Guarantees. NeurIPS Sharan Vaswani, Amirreza Kazemi, Reza Babanezhad Harikandeh, Nicolas Le Roux
2023	J	`jnl`	Decision-Aware Actor-Critic with Function Approximation and Theoretical Guarantees. CoRR Sharan Vaswani, Amirreza Kazemi, Reza Babanezhad, Nicolas Le Roux
2023	J	`jnl`	Deep Language Networks: Joint Prompt Training of Stacked LLMs using Variational Inference. CoRR Alessandro Sordoni, Xingdi Yuan, Marc-Alexandre Côté, Matheus Pereira, Adam Trischler, Ziang Xiao, Arian Hosseini, Friederike Niedtner, Nicolas Le Roux
2023	A*	`conf`	Joint Prompt Optimization of Stacked LLMs using Variational Inference. NeurIPS Alessandro Sordoni, Eric Yuan, Marc-Alexandre Côté, Matheus Pereira, Adam Trischler, Ziang Xiao, Arian Hosseini, Friederike Niedtner, Nicolas Le Roux
2023	A*	`conf`	Multi-Head Adapter Routing for Cross-Task Generalization. NeurIPS Lucas Page-Caccia, Edoardo Maria Ponti, Zhan Su, Matheus Pereira, Nicolas Le Roux, Alessandro Sordoni
2023	A*	`conf`	Target-based Surrogates for Stochastic Optimization. ICML Jonathan Wilder Lavington, Sharan Vaswani, Reza Babanezhad Harikandeh, Mark Schmidt, Nicolas Le Roux
2023	J	`jnl`	Target-based Surrogates for Stochastic Optimization. CoRR Jonathan Wilder Lavington, Sharan Vaswani, Reza Babanezhad, Mark Schmidt, Nicolas Le Roux
2023	—	`conf`	Unraveling the Interconnected Axes of Heterogeneity in Machine Learning for Democratic and Inclusive Advancements. EAAMO Maryam Molamohammadi, Afaf Taïk, Nicolas Le Roux, Golnoosh Farnadi
2023	J	`jnl`	Unraveling the Interconnected Axes of Heterogeneity in Machine Learning for Democratic and Inclusive Advancements. CoRR Maryam Molamohammadi, Afaf Taïk, Nicolas Le Roux, Golnoosh Farnadi
2022	A	`conf`	A general class of surrogate functions for stable and efficient reinforcement learning. AISTATS Sharan Vaswani, Olivier Bachem, Simone Totaro, Robert Müller, Shivam Garg, Matthieu Geist, Marlos C. Machado, Pablo Samuel Castro, Nicolas Le Roux
2022	J	`jnl`	Multi-Head Adapter Routing for Data-Efficient Fine-Tuning. CoRR Lucas Caccia, Edoardo Maria Ponti, Lucas Liu, Matheus Pereira, Nicolas Le Roux, Alessandro Sordoni
2022	A	`conf`	On the Convergence of Stochastic Extragradient for Bilinear Games using Restarted Iteration Averaging. AISTATS Chris Junchi Li, Yaodong Yu, Nicolas Loizou, Gauthier Gidel, Yi Ma, Nicolas Le Roux, Michael I. Jordan
2021	J	`jnl`	A functional mirror ascent view of policy gradient methods with function approximation. CoRR Sharan Vaswani, Olivier Bachem, Simone Totaro, Robert Mueller, Matthieu Geist, Marlos C. Machado, Pablo Samuel Castro, Nicolas Le Roux
2021	A*	`conf`	Batch Reinforcement Learning Through Continuation Method. ICLR Yijie Guo, Shengyu Feng, Nicolas Le Roux, Ed H. Chi, Honglak Lee, Minmin Chen
2021	A*	`conf`	Beyond Variance Reduction: Understanding the True Impact of Baselines on Policy Optimization. ICML Wesley Chung, Valentin Thomas, Marlos C. Machado, Nicolas Le Roux
2021	J	`jnl`	Bridging the Gap Between Adversarial Robustness and Optimization Bias. CoRR Fartash Faghri, Cristina Nader Vasconcelos, David J. Fleet, Fabian Pedregosa, Nicolas Le Roux
2021	A*	`conf`	Impact of Aliasing on Generalization in Deep Convolutional Networks. ICCV Cristina Nader Vasconcelos, Hugo Larochelle, Vincent Dumoulin, Rob Romijnders, Nicolas Le Roux, Ross Goroshin
2021	J	`jnl`	Impact of Aliasing on Generalization in Deep Convolutional Networks. CoRR Cristina Nader Vasconcelos, Hugo Larochelle, Vincent Dumoulin, Rob Romijnders, Nicolas Le Roux, Ross Goroshin
2021	J	`jnl`	On the Convergence of Stochastic Extragradient for Bilinear Games with Restarted Iteration Averaging. CoRR Chris Junchi Li, Yaodong Yu, Nicolas Loizou, Gauthier Gidel, Yi Ma, Nicolas Le Roux, Michael I. Jordan
2020	J	`jnl`	An Effective Anti-Aliasing Approach for Residual Networks. CoRR Cristina Nader Vasconcelos, Hugo Larochelle, Vincent Dumoulin, Nicolas Le Roux, Ross Goroshin
2020	A*	`conf`	An operator view of policy gradient methods. NeurIPS Dibya Ghosh, Marlos C. Machado, Nicolas Le Roux
2020	J	`jnl`	An operator view of policy gradient methods. CoRR Dibya Ghosh, Marlos C. Machado, Nicolas Le Roux
2020	J	`jnl`	Beyond variance reduction: Understanding the true impact of baselines on policy optimization. CoRR Wesley Chung, Valentin Thomas, Marlos C. Machado, Nicolas Le Roux
2020	A	`conf`	On the interplay between noise and curvature and its effect on optimization and generalization. AISTATS Valentin Thomas, Fabian Pedregosa, Bart van Merriënboer, Pierre-Antoine Manzagol, Yoshua Bengio, Nicolas Le Roux
2020	J	`jnl`	The Geometry of Sign Gradient Descent. CoRR Lukas Balles, Fabian Pedregosa, Nicolas Le Roux
2020	J	`jnl`	To Each Optimizer a Norm, To Each Norm its Generalization. CoRR Sharan Vaswani, Reza Babanezhad, Jose Gallego, Aaron Mishkin, Simon Lacoste-Julien, Nicolas Le Roux
2019	A*	`conf`	A Geometric Perspective on Optimal Representations for Reinforcement Learning. NeurIPS Marc G. Bellemare, Will Dabney, Robert Dadashi, Adrien Ali Taïga, Pablo Samuel Castro, Nicolas Le Roux, Dale Schuurmans, Tor Lattimore, Clare Lyle
2019	J	`jnl`	A Geometric Perspective on Optimal Representations for Reinforcement Learning. CoRR Marc G. Bellemare, Will Dabney, Robert Dadashi, Adrien Ali Taïga, Pablo Samuel Castro, Nicolas Le Roux, Dale Schuurmans, Tor Lattimore, Clare Lyle
2019	J	`jnl`	Anytime Tail Averaging. CoRR Nicolas Le Roux
2019	A	`conf`	Distributional reinforcement learning with linear function approximation. AISTATS Marc G. Bellemare, Nicolas Le Roux, Pablo Samuel Castro, Subhodeep Moitra
2019	J	`jnl`	Distributional reinforcement learning with linear function approximation. CoRR Marc G. Bellemare, Nicolas Le Roux, Pablo Samuel Castro, Subhodeep Moitra
2019	J	`jnl`	Information matrices and generalization. CoRR Valentin Thomas, Fabian Pedregosa, Bart van Merriënboer, Pierre-Antoine Manzagol, Yoshua Bengio, Nicolas Le Roux
2019	J	`jnl`	Negative eigenvalues of the Hessian in deep neural networks. CoRR Guillaume Alain, Nicolas Le Roux, Pierre-Antoine Manzagol
2019	A*	`conf`	Reducing the variance in online optimization by transporting past gradients. NeurIPS Sébastien M. R. Arnold, Pierre-Antoine Manzagol, Reza Babanezhad, Ioannis Mitliagkas, Nicolas Le Roux
2019	J	`jnl`	Reducing the variance in online optimization by transporting past gradients. CoRR Sébastien M. R. Arnold, Pierre-Antoine Manzagol, Reza Babanezhad, Ioannis Mitliagkas, Nicolas Le Roux
2019	A*	`conf`	The Value Function Polytope in Reinforcement Learning. ICML Robert Dadashi, Marc G. Bellemare, Adrien Ali Taïga, Nicolas Le Roux, Dale Schuurmans
2019	J	`jnl`	The Value Function Polytope in Reinforcement Learning. CoRR Robert Dadashi, Adrien Ali Taïga, Nicolas Le Roux, Dale Schuurmans, Marc G. Bellemare
2019	A*	`conf`	Understanding the Impact of Entropy on Policy Optimization. ICML Zafarali Ahmed, Nicolas Le Roux, Mohammad Norouzi, Dale Schuurmans
2018	—	`conf`	Negative eigenvalues of the Hessian in deep neural networks. ICLR (Workshop) Guillaume Alain, Nicolas Le Roux, Pierre-Antoine Manzagol
2018	—	`conf`	Online variance-reducing optimization. ICLR (Workshop) Nicolas Le Roux, Reza Babanezhad, Pierre-Antoine Manzagol
2018	A	`conf`	Tracking the gradients using the Hessian: A new look at variance reducing stochastic methods. AISTATS Robert M. Gower, Nicolas Le Roux, Francis R. Bach
2018	J	`jnl`	Understanding the impact of entropy on policy optimization. CoRR Zafarali Ahmed, Nicolas Le Roux, Mohammad Norouzi, Dale Schuurmans
2017	J	`jnl`	A comparative study of counterfactual estimators. CoRR Thomas Nedelec, Nicolas Le Roux, Vianney Perchet
2017	J	`jnl`	Distributed SAGA: Maintaining linear convergence rate with limited communication. CoRR Clément Calauzènes, Nicolas Le Roux
2017	J	`jnl`	Erratum to: Minimizing finite sums with the stochastic average gradient. Math. Program. Mark Schmidt, Nicolas Le Roux, Francis R. Bach
2017	J	`jnl`	Minimizing finite sums with the stochastic average gradient. Math. Program. Mark Schmidt, Nicolas Le Roux, Francis R. Bach
2017	—	`conf`	Tighter bounds lead to improved classifiers. ICLR (Poster) Nicolas Le Roux
2017	J	`jnl`	Tracking the gradients using the Hessian: A new look at variance reducing stochastic methods. CoRR Robert M. Gower, Nicolas Le Roux, Francis R. Bach
2016	J	`jnl`	Efficient iterative policy optimization. CoRR Nicolas Le Roux
2016	J	`jnl`	Tighter bounds lead to improved classifiers. CoRR Nicolas Le Roux
2015	A	`conf`	Large-Scale Real-Time Product Recommendation at Criteo. RecSys Romain Lerallut, Diane Gasselin, Nicolas Le Roux
2013	A*	`conf`	Local Component Analysis ICLR (Poster) Nicolas Le Roux, Francis R. Bach
2013	J	`jnl`	Minimizing Finite Sums with the Stochastic Average Gradient. CoRR Mark Schmidt, Nicolas Le Roux, Francis R. Bach
2012	—	`conf`	A Stochastic Gradient Method with an Exponential Convergence Rate for Finite Training Sets. NIPS Nicolas Le Roux, Mark Schmidt, Francis R. Bach
2012	J	`jnl`	A Stochastic Gradient Method with an Exponential Convergence Rate for Strongly-Convex Optimization with Finite Training Sets CoRR Nicolas Le Roux, Mark Schmidt, Francis R. Bach
2012	—	`conf`	A latent factor model for highly multi-relational data. NIPS Rodolphe Jenatton, Nicolas Le Roux, Antoine Bordes, Guillaume Obozinski
2011	A*	`conf`	Ask the locals: Multi-way local pooling for image recognition. ICCV Y-Lan Boureau, Nicolas Le Roux, Francis R. Bach, Jean Ponce, Yann LeCun
2011	J	`jnl`	Convergence Rates of Inexact Proximal-Gradient Methods for Convex Optimization CoRR Mark Schmidt, Nicolas Le Roux, Francis R. Bach
2011	—	`conf`	Convergence Rates of Inexact Proximal-Gradient Methods for Convex Optimization. NIPS Mark Schmidt, Nicolas Le Roux, Francis R. Bach
2011	J	`jnl`	Learning a Generative Model of Images by Factoring Appearance and Shape. Neural Comput. Nicolas Le Roux, Nicolas Heess, Jamie Shotton, John M. Winn
2011	—	`conf`	Weakly Supervised Learning of Foreground-Background Segmentation Using Masked RBMs. ICANN (2) Nicolas Heess, Nicolas Le Roux, John M. Winn
2011	J	`jnl`	Weakly Supervised Learning of Foreground-Background Segmentation using Masked RBMs CoRR Nicolas Heess, Nicolas Le Roux, John M. Winn
2010	A*	`conf`	A fast natural Newton method. ICML Nicolas Le Roux, Andrew W. Fitzgibbon
2010	J	`jnl`	Deep Belief Networks Are Compact Universal Approximators. Neural Comput. Nicolas Le Roux, Yoshua Bengio
2008	J	`jnl`	Products of Ordinary Differential Operators by Evaluation and Interpolation CoRR Alin Bostan, Frédéric Chyzak, Nicolas Le Roux
2008	B	`conf`	Products of ordinary differential operators by evaluation and interpolation. ISSAC Alin Bostan, Frédéric Chyzak, Nicolas Le Roux
2008	J	`jnl`	Representational Power of Restricted Boltzmann Machines and Deep Belief Networks. Neural Comput. Nicolas Le Roux, Yoshua Bengio
2007	A	`conf`	Continuous Neural Networks. AISTATS Nicolas Le Roux, Yoshua Bengio
2007	—	`conf`	Learning the 2-D Topology of Images. NIPS Nicolas Le Roux, Yoshua Bengio, Pascal Lamblin, Marc Joliveau, Balázs Kégl
2007	—	`conf`	Topmoumoute Online Natural Gradient Algorithm. NIPS Nicolas Le Roux, Pierre-Antoine Manzagol, Yoshua Bengio
2006	—	`ch.`	Label Propagation and Quadratic Criterion. Semi-Supervised Learning Yoshua Bengio, Olivier Delalleau, Nicolas Le Roux
2006	—	`ch.`	Large-Scale Algorithms. Semi-Supervised Learning Olivier Delalleau, Yoshua Bengio, Nicolas Le Roux
2006	B	`conf`	Rank reduction of a class of pfaffian systems in two variables. ISSAC Nicolas Le Roux, Moulay A. Barkatou
2006	—	`ch.`	Spectral Dimensionality Reduction. Feature Extraction Yoshua Bengio, Olivier Delalleau, Nicolas Le Roux, Jean-François Paiement, Pascal Vincent, Marie Ouimet
2005	—	`conf`	Convex Neural Networks. NIPS Yoshua Bengio, Nicolas Le Roux, Pascal Vincent, Olivier Delalleau, Patrice Marcotte
2005	A	`conf`	Efficient Non-Parametric Function Induction in Semi-Supervised Learning. AISTATS Olivier Delalleau, Yoshua Bengio, Nicolas Le Roux
2005	—	`conf`	The Curse of Highly Variable Functions for Local Kernel Machines. NIPS Yoshua Bengio, Olivier Delalleau, Nicolas Le Roux
2004	J	`jnl`	Learning Eigenfunctions Links Spectral Embedding and Kernel PCA. Neural Comput. Yoshua Bengio, Olivier Delalleau, Nicolas Le Roux, Jean-François Paiement, Pascal Vincent, Marie Ouimet
2003	B	`conf`	Computing power series solutions of a nonlinear PDE system. ISSAC Evelyne Hubert, Nicolas Le Roux
2003	—	`conf`	Out-of-Sample Extensions for LLE, Isomap, MDS, Eigenmaps, and Spectral Clustering. NIPS Yoshua Bengio, Jean-François Paiement, Pascal Vincent, Olivier Delalleau, Nicolas Le Roux, Marie Ouimet