Heterogeneous federated learning: State-of-the-art and research challenges

M Ye, X Fang, B Du, PC Yuen, D Tao - ACM Computing Surveys, 2023 - dl.acm.org
Federated learning (FL) has drawn increasing attention owing to its potential use in large-
scale industrial applications. Existing FL works mainly focus on model homogeneous …

On particle methods for parameter estimation in state-space models

N Kantas, A Doucet, SS Singh, J Maciejowski… - 2015 - projecteuclid.org
Nonlinear non-Gaussian state-space models are ubiquitous in statistics, econometrics,
information engineering and signal processing. Particle methods, also known as Sequential …

Self-supervised graph-level representation learning with local and global structure

M Xu, H Wang, B Ni, H Guo… - … Conference on Machine …, 2021 - proceedings.mlr.press
This paper studies unsupervised/self-supervised whole-graph representation learning,
which is critical in many tasks such as molecule properties prediction in drug and material …

[HTML][HTML] Machine learning in acoustics: Theory and applications

MJ Bianco, P Gerstoft, J Traer, E Ozanich… - The Journal of the …, 2019 - pubs.aip.org
Acoustic data provide scientific and engineering insights in fields ranging from biology and
communications to ocean and Earth science. We survey the recent advances and …

A consolidated perspective on multimicrophone speech enhancement and source separation

S Gannot, E Vincent… - … /ACM Transactions on …, 2017 - ieeexplore.ieee.org
Speech enhancement and separation are core problems in audio signal processing, with
commercial applications in devices as diverse as mobile phones, conference call systems …

[PDF][PDF] Stochastic variational inference

MD Hoffman, DM Blei, C Wang, J Paisley - Journal of Machine Learning …, 2013 - jmlr.org
We develop stochastic variational inference, a scalable algorithm for approximating
posterior distributions. We develop this technique for a large class of probabilistic models …

Statistical guarantees for the EM algorithm: From population to sample-based analysis

S Balakrishnan, MJ Wainwright, B Yu - 2017 - projecteuclid.org
Statistical guarantees for the EM algorithm: From population to sample-based analysis Page 1
The Annals of Statistics 2017, Vol. 45, No. 1, 77–120 DOI: 10.1214/16-AOS1435 © Institute of …

Streaming fragment assignment for real-time analysis of sequencing experiments

A Roberts, L Pachter - Nature methods, 2013 - nature.com
We present eXpress, a software package for efficient probabilistic assignment of
ambiguously map** sequenced fragments. eXpress uses a streaming algorithm with …

Multi-center federated learning: clients clustering for better personalization

G Long, M **e, T Shen, T Zhou, X Wang, J Jiang - World Wide Web, 2023 - Springer
Personalized decision-making can be implemented in a Federated learning (FL) framework
that can collaboratively train a decision model by extracting knowledge across intelligent …

Rl for latent mdps: Regret guarantees and a lower bound

J Kwon, Y Efroni, C Caramanis… - Advances in Neural …, 2021 - proceedings.neurips.cc
In this work, we consider the regret minimization problem for reinforcement learning in latent
Markov Decision Processes (LMDP). In an LMDP, an MDP is randomly drawn from a set of …