fourier convolutions 1irregular sampling 1neural processes 1translation equivariance 1volterra series 1
From the 1 of 3 linked papers with an AI index.
3 papers
cs.LG2026
Revisiting Neural Processes via Fourier Transform and Volterra Series
Peiman Mohseni, Nick Duffield, Raymond K. W. Wong
The paper introduces translation‑equivariant neural processes that use a Volterra series expansion and set Fourier convolutions to model irregularly sampled data with analytical tr…
cs.LG2026
Spectral Convolutional Conditional Neural Processes
Peiman Mohseni, Nick Duffield
Neural Processes (NPs) are meta-learning models that learn to map sets of observations to approximations of the corresponding posterior predictive distributions. By accommodating v…
cs.LG2025
QoS-Efficient Serving of Multiple Mixture-of-Expert LLMs Using Partial Runtime Reconfiguration
HamidReza Imani, Jiaxin Peng, Peiman Mohseni +2
The deployment of mixture-of-experts (MoE) large language models (LLMs) presents significant challenges due to their high memory demands. These challenges become even more pronounc…