3.4k citations
- Google (United States)US56 papers
- Google (United Kingdom)GB17 papers
- University of TorontoCA7 papers
- Centre de Recherche en InformatiqueFR6 papers
- Centre de Recherche en Informatique, Signal et Automatique de LilleFR6 papers
- University of AlbertaCA6 papers
- University of OxfordGB6 papers
- Carnegie Mellon UniversityUS5 papers
- Columbia UniversityUS5 papers
- McGill UniversityCA5 papers
- Afterschool AllianceUS4 papers
- École Normale Supérieure - PSLFR4 papers
66 papers · 1 filter
AtP*: An efficient and scalable method for localizing LLM behaviour to components
János Kramár, Tom Lieberum, Rohin Shah +1
Activation Patching is a method of directly computing causal attributions of behavior to model components. However, applying it exhaustively requires a sweep with cost scaling line…
Half-Hop: A graph upsampling approach for slowing down message passing
Mehdi Azabou, Venkataramana Ganesh, Shantanu Thakoor +6
Message passing neural networks have shown a lot of success on graph-structured data. However, there are many instances where message passing can lead to over-smoothing or fail whe…
DoMo-AC: Doubly Multi-step Off-policy Actor-Critic Algorithm
Yunhao Tang, Tadashi Kozuno, Mark Rowland +4
Multi-step learning applies lookahead over multiple time steps and has proved valuable in policy evaluation settings. However, in the optimal control case, the impact of multi-step…
Regularization and Variance-Weighted Regression Achieves Minimax Optimality in Linear MDPs: Theory and Practice
Toshinori Kitamura, Tadashi Kozuno, Yunhao Tang +12
Mirror descent value iteration (MDVI), an abstraction of Kullback-Leibler (KL) and entropy-regularized reinforcement learning (RL), has served as the basis for recent high-performi…
Unlocking the Power of Representations in Long-term Novelty-based Exploration
Alaa Saade, Steven Kapturowski, Daniele Calandriello +6
We introduce Robust Exploration via Clustering-based Online Density Estimation (RECODE), a non-parametric method for novelty-based exploration that estimates visitation counts for…
Fast, Differentiable and Sparse Top-k: a Convex Analysis Perspective
Michael E. Sander, Joan Puigcerver, Josip Djolonga +2
The top-k operator returns a sparse vector, where the non-zero values correspond to the k largest values of the input. Unfortunately, because it is a discontinuous function, it is…