Serverless federated auprc optimization for multi-party collaborative imbalanced data mining
To address the big data challenges, serverless multi-party collaborative training has recently
attracted attention in the data mining community, since they can cut down the …
attracted attention in the data mining community, since they can cut down the …
Prometheus: taming sample and communication complexities in constrained decentralized stochastic bilevel learning
In recent years, decentralized bilevel optimization has gained significant attention thanks to
its versatility in modeling a wide range of multi-agent learning problems, such as multi-agent …
its versatility in modeling a wide range of multi-agent learning problems, such as multi-agent …
On the communication complexity of decentralized bilevel optimization
Decentralized bilevel optimization has been actively studied in the past few years since it
has widespread applications in machine learning. However, existing algorithms suffer from …
has widespread applications in machine learning. However, existing algorithms suffer from …
Decentralized Bilevel Optimization over Graphs: Loopless Algorithmic Update and Transient Iteration Complexity
Stochastic bilevel optimization (SBO) is becoming increasingly essential in machine
learning due to its versatility in handling nested structures. To address large-scale SBO …
learning due to its versatility in handling nested structures. To address large-scale SBO …
DePRL: Achieving Linear Convergence Speedup in Personalized Decentralized Learning with Shared Representations
Decentralized learning has emerged as an alternative method to the popular parameter-
server framework which suffers from high communication burden, single-point failure and …
server framework which suffers from high communication burden, single-point failure and …
DIAMOND: Taming Sample and Communication Complexities in Decentralized Bilevel Optimization
Decentralized bilevel optimization has received increasing attention recently due to its
foundational role in many emerging multi-agent learning paradigms (eg, multi-agent meta …
foundational role in many emerging multi-agent learning paradigms (eg, multi-agent meta …
Personalized decentralized bilevel optimization over stochastic and directed networks
N Terashita, S Hara - 2022 - openreview.net
While personalization in distributed learning has been extensively studied, existing
approaches employ dedicated algorithms to optimize their specific type of parameters (eg …
approaches employ dedicated algorithms to optimize their specific type of parameters (eg …
Decentralized Hyper-Gradient Computation over Time-Varying Directed Networks
N Terashita, S Hara - arXiv preprint arXiv:2210.02129, 2022 - arxiv.org
This paper addresses the communication issues when estimating hyper-gradients in
decentralized federated learning (FL). Hyper-gradients in decentralized FL quantifies how …
decentralized federated learning (FL). Hyper-gradients in decentralized FL quantifies how …
A Method for Deductive Failure Analysis with Probabilistic Augmentation: BLIPS-PA
A Mansoor - 2023 - rave.ohiolink.edu
This research can be divided into two aspects: the development of a deductive failure
analysis method for Backwards Logic Inference based Propagation for System analysis …
analysis method for Backwards Logic Inference based Propagation for System analysis …
Prometheus: Endowing Low Sample and Communication Complexities to Constrained Decentralized Stochastic Bilevel Learning
In recent years, constrained decentralized stochastic bilevel optimization has become
increasingly important due to its versatility in modeling a wide range of multi-agent learning …
increasingly important due to its versatility in modeling a wide range of multi-agent learning …