Federated reconstruction: Partially local federated learning
Personalization methods in federated learning aim to balance the benefits of federated and
local training for data availability, communication cost, and robustness to client …
local training for data availability, communication cost, and robustness to client …
On sparse modern hopfield model
We introduce the sparse modern Hopfield model as a sparse extension of the modern
Hopfield model. Like its dense counterpart, the sparse modern Hopfield model equips a …
Hopfield model. Like its dense counterpart, the sparse modern Hopfield model equips a …
Modeling heterogeneity in random graphs through latent space models: a selective review
Modeling heterogeneity in random graphs through latent space models: a selective review\*
Page 1 ESAIM: PROCEEDINGS AND SURVEYS, December 2014, Vol. 47, p. 55-74 F …
Page 1 ESAIM: PROCEEDINGS AND SURVEYS, December 2014, Vol. 47, p. 55-74 F …
Statistical clustering of temporal networks through a dynamic stochastic block model
C Matias, V Miele - Journal of the Royal Statistical Society Series …, 2017 - academic.oup.com
Statistical node clustering in discrete time dynamic networks is an emerging field that raises
many challenges. Here, we explore statistical properties and frequentist inference in a …
many challenges. Here, we explore statistical properties and frequentist inference in a …
Adaptive fusion and category-level dictionary learning model for multiview human action recognition
Human actions are often captured by multiple cameras (or sensors) to overcome the
significant variations in viewpoints, background clutter, object speed, and motion patterns in …
significant variations in viewpoints, background clutter, object speed, and motion patterns in …
On stochastic optimal control and reinforcement learning by approximate inference
We present a reformulation of the stochastic optimal control problem in terms of KL
divergence minimisation, not only providing a unifying perspective of previous approaches …
divergence minimisation, not only providing a unifying perspective of previous approaches …
[PDF][PDF] On the Convergence of the Concave-Convex Procedure.
The concave-convex procedure (CCCP) is a majorization-minimization algorithm that solves
dc (difference of convex functions) programs as a sequence of convex programs. In machine …
dc (difference of convex functions) programs as a sequence of convex programs. In machine …
On the convergence of the concave-convex procedure
The concave-convex procedure (CCCP) is a majorization-minimization algorithm that solves
dc (difference of convex functions) programs as a sequence of convex programs. In machine …
dc (difference of convex functions) programs as a sequence of convex programs. In machine …
Riemannian dictionary learning and sparse coding for positive definite matrices
Data encoded as symmetric positive definite (SPD) matrices frequently arise in many areas
of computer vision and machine learning. While these matrices form an open subset of the …
of computer vision and machine learning. While these matrices form an open subset of the …
Multi-modal clique-graph matching for view-based 3D model retrieval
Multi-view matching is an important but a challenging task in view-based 3D model retrieval.
To address this challenge, we propose an original multi-modal clique graph (MCG) …
To address this challenge, we propose an original multi-modal clique graph (MCG) …