4 papers · 1 filter
The Diffusion-Attention Connection
Julio Candanedo
Softmax attention is the row-normalized operator of a diffusion map: both normalize a learned score into a Markov operator, and differ only in what the score is allowed to contain.…
Diffusion Maps is not Dimensionality Reduction
Julio Candanedo, Alejandro Patiño
Diffusion maps (DMAP) are often used as a dimensionality-reduction tool, but more precisely they provide a spectral representation of the intrinsic geometry rather than a complete…
LISA: Laplacian In-context Spectral Analysis
Julio Candanedo
We propose Laplacian In-context Spectral Analysis (LISA), a method for inference-time adaptation of Laplacian-based time-series models using only an observed prefix. LISA combines…
Linearized Diffusion Map
Julio Candanedo
We introduce the Linearized Diffusion Map (LDM), a novel linear dimensionality reduction method constructed via a linear approximation of the diffusion-map kernel. LDM integrates t…