3 papers
cs.LG2026
Model Casting and Low-Parameter Gating: Towards More Sparsely Activated FFNs
Maria Lomeli, Antoine Groudiev, Matthijs Douze +7
This paper introduces model casting, a mid-training recipe that drastically sparsifies the activations within the Feed-Forward Network (FFN) layer. With this strategy, at inference…
cs.RO2025
Sampling-Based Global Optimal Control and Estimation via Semidefinite Programming
Antoine Groudiev, Fabian Schramm, Éloïse Berthier +2
Global optimization has gained attraction over the past decades, thanks to the development of both theoretical foundations and efficient numerical routines. Among recent advances,…
math.OC2025
Factorization-free Orthogonal Projection onto the Positive Semidefinite Cone with Composite Polynomial Filtering
Shucheng Kang, Haoyu Han, Antoine Groudiev +1
We propose a factorization-free method for orthogonal projection onto the positive semidefinite (PSD) cone, leveraging composite polynomial filtering. Inspired by recent advances i…