Federated reconstruction: Partially local federated learning

K Singhal, H Sidahmed, Z Garrett… - Advances in …, 2021 - proceedings.neurips.cc
Personalization methods in federated learning aim to balance the benefits of federated and
local training for data availability, communication cost, and robustness to client …

On sparse modern hopfield model

JYC Hu, D Yang, D Wu, C Xu… - Advances in Neural …, 2024 - proceedings.neurips.cc
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 …

Modeling heterogeneity in random graphs through latent space models: a selective review

C Matias, S Robin - ESAIM: Proceedings and Surveys, 2014 - esaim-proc.org
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 …

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 …

Adaptive fusion and category-level dictionary learning model for multiview human action recognition

Z Gao, HZ Xuan, H Zhang, S Wan… - IEEE Internet of Things …, 2019 - ieeexplore.ieee.org
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 …

On stochastic optimal control and reinforcement learning by approximate inference

K Rawlik, M Toussaint, S Vijayakumar - 2013 - direct.mit.edu
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 …

[PDF][PDF] On the Convergence of the Concave-Convex Procedure.

BK Sriperumbudur, GRG Lanckriet - Nips, 2009 - Citeseer
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 …

On the convergence of the concave-convex procedure

G Lanckriet, BK Sriperumbudur - Advances in neural …, 2009 - proceedings.neurips.cc
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 …

Riemannian dictionary learning and sparse coding for positive definite matrices

A Cherian, S Sra - IEEE transactions on neural networks and …, 2016 - ieeexplore.ieee.org
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 …

Multi-modal clique-graph matching for view-based 3D model retrieval

AA Liu, WZ Nie, Y Gao, YT Su - IEEE Transactions on Image …, 2016 - ieeexplore.ieee.org
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) …