🏢 Inria

MetaCURL: First algorithm for non-stationary Concave Utility Reinforcement Learning (CURL), achieving near-optimal dynamic regret by using a meta-algorithm and sleeping experts framework.

Surrogate PAC-Bayes Learning (SuPAC) efficiently optimizes generalization bounds by iteratively optimizing surrogate training objectives, enabling faster and more scalable learning for complex models.

Boosting neural network surface processing: Using principal curvatures as input significantly improves segmentation and classification accuracy while reducing computational overhead.

GOPSA: a novel geodesic optimization method significantly improves cross-site age prediction from EEG data by jointly handling shifts in data and predictive variables.

First near-optimal reinforcement learning algorithm achieving best policy identification in average-reward MDPs without prior knowledge of complexity.

DU-Shapley efficiently estimates the Shapley value for dataset valuation, enabling fair compensation in collaborative machine learning by leveraging the problem’s structure for faster computation.

Hierarchical concept bottleneck models boost interpretability and accuracy in visual classification by uncovering both high-level and low-level concepts.

Randomness-efficient algorithms are developed for online decision making, requiring only 2log n random bits and achieving near-optimal competitiveness for metrical task systems.

Autotelic Code Search (ACES) generates diverse, challenging Python programming puzzles by iteratively using LLM-generated semantic descriptors and measuring puzzle difficulty via LLM solver success ra…