2 papers
stat.ML2025
Splat Regression Models
Mara Daniels, Philippe Rigollet
We introduce a highly expressive class of function approximators called Splat Regression Models. Model outputs are mixtures of heterogeneous and anisotropic bump functions, termed…
cs.LG2025
The power of fine-grained experts: Granularity boosts expressivity in Mixture of Experts
Enric Boix-Adsera, Philippe Rigollet
Mixture-of-Experts (MoE) layers are increasingly central to frontier model architectures. By selectively activating parameters, they reduce computational cost while scaling total p…