Picture for Loris Cannelli

Loris Cannelli

Gradient-based bilevel optimization for multi-penalty Ridge regression through matrix differential calculus

Add code
Nov 23, 2023
Viaarxiv icon

Split-Boost Neural Networks

Add code
Sep 06, 2023
Viaarxiv icon

Hedging using reinforcement learning: Contextual $k$-Armed Bandit versus $Q$-learning

Add code
Jul 03, 2020
Figure 1 for Hedging using reinforcement learning: Contextual $k$-Armed Bandit versus $Q$-learning
Figure 2 for Hedging using reinforcement learning: Contextual $k$-Armed Bandit versus $Q$-learning
Figure 3 for Hedging using reinforcement learning: Contextual $k$-Armed Bandit versus $Q$-learning
Figure 4 for Hedging using reinforcement learning: Contextual $k$-Armed Bandit versus $Q$-learning
Viaarxiv icon