Heterogeneous federated learning: State-of-the-art and research challenges
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 …
scale industrial applications. Existing FL works mainly focus on model homogeneous …
On particle methods for parameter estimation in state-space models
Nonlinear non-Gaussian state-space models are ubiquitous in statistics, econometrics,
information engineering and signal processing. Particle methods, also known as Sequential …
information engineering and signal processing. Particle methods, also known as Sequential …
Self-supervised graph-level representation learning with local and global structure
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 …
which is critical in many tasks such as molecule properties prediction in drug and material …
[HTML][HTML] Machine learning in acoustics: Theory and applications
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 …
communications to ocean and Earth science. We survey the recent advances and …
A consolidated perspective on multimicrophone speech enhancement and source separation
Speech enhancement and separation are core problems in audio signal processing, with
commercial applications in devices as diverse as mobile phones, conference call systems …
commercial applications in devices as diverse as mobile phones, conference call systems …
[PDF][PDF] Stochastic variational inference
We develop stochastic variational inference, a scalable algorithm for approximating
posterior distributions. We develop this technique for a large class of probabilistic models …
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
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 …
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
We present eXpress, a software package for efficient probabilistic assignment of
ambiguously map** sequenced fragments. eXpress uses a streaming algorithm with …
ambiguously map** sequenced fragments. eXpress uses a streaming algorithm with …
Multi-center federated learning: clients clustering for better personalization
Personalized decision-making can be implemented in a Federated learning (FL) framework
that can collaboratively train a decision model by extracting knowledge across intelligent …
that can collaboratively train a decision model by extracting knowledge across intelligent …
Rl for latent mdps: Regret guarantees and a lower bound
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 …
Markov Decision Processes (LMDP). In an LMDP, an MDP is randomly drawn from a set of …