Nicolas Le Roux

23 papers · 2018–2025 · 6 conferences · across top CS/AI conferences

Achievements

+7 more ↓

🌍 Conference Polyglot (6) 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🌉 Interdisciplinary Bridge 🏃 Academic Marathon (7)

🌍 Conference Polyglot (6) 🏃 Academic Marathon (7) 🧭 Keyword Pioneer 🗃️ Keyword Collector (92) 💎 Century Club (23) 🔥 Unstoppable (8) ⚡ Prolific Year (5)

Conferences

ICML (7) NIPS (7) AISTATS (6) EMNLP (1) ICCV (1) ICLR (1)

Top co-authors

Alessandro Sordoni (5) Sharan Vaswani (4) Reza Babanezhad Harikandeh (4) Marlos C. Machado (3) Pablo Samuel Castro (3) Dale Schuurmans (3) Ziang Xiao (2) Zhan Su (2) Marc G. Bellemare (2) Valentin Thomas (2)

Keywords

policy optimization (4) stochastic optimization (3) variance reduction (3) large language model (3) representation learning (2) policy gradient (2) reinforcement learning (2) surrogate function (2) geometric analysis (2) convergence rate (2) value function (2) temporal difference learning (1) variational inference (1) function approximation (1) stochastic gradient descent (1) imitation learning (1) text generation (1) few-shot learning (1) data augmentation (1) natural policy gradient (1)

Papers

VinePPO: Refining Credit Assignment in RL Training of LLMs ICML 2025 Fast Convergence of Softmax Policy Mirror Ascent AISTATS 2025 fLSA: Learning Semantic Structures in Document Collections Using Foundation Models EMNLP 2025 Improving Context-Aware Preference Modeling for Language Models NIPS 2024 Language-guided Skill Learning with Temporal Variational Inference ICML 2024 Towards Modular LLMs by Building and Reusing a Library of LoRAs ICML 2024 Multi-Head Adapter Routing for Cross-Task Generalization NIPS 2023 Target-based Surrogates for Stochastic Optimization ICML 2023 Joint Prompt Optimization of Stacked LLMs using Variational Inference NIPS 2023 Decision-Aware Actor-Critic with Function Approximation and Theoretical Guarantees NIPS 2023 On the Convergence of Stochastic Extragradient for Bilinear Games using Restarted Iteration Averaging AISTATS 2022 A general class of surrogate functions for stable and efficient reinforcement learning AISTATS 2022 Impact of Aliasing on Generalization in Deep Convolutional Networks ICCV 2021 Beyond Variance Reduction: Understanding the True Impact of Baselines on Policy Optimization ICML 2021 Batch Reinforcement Learning Through Continuation Method ICLR 2021 An operator view of policy gradient methods NIPS 2020 On the interplay between noise and curvature and its effect on optimization and generalization AISTATS 2020 A Geometric Perspective on Optimal Representations for Reinforcement Learning NIPS 2019 Understanding the Impact of Entropy on Policy Optimization ICML 2019 The Value Function Polytope in Reinforcement Learning ICML 2019 Distributional reinforcement learning with linear function approximation AISTATS 2019 Reducing the variance in online optimization by transporting past gradients NIPS 2019 Tracking the gradients using the Hessian: A new look at variance reducing stochastic methods AISTATS 2018