.png){kind=icon}
.png){kind=icon}
Return
Quantized Zeroth-Order Gradient Tracking Algorithm for Distributed Nonconvex Optimization Under Polyak-Lojasiewicz Condition
.png){kind=icon}
PRE
AI
DOI：10.1109/TCYB.2024.3384924.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
This article focuses on distributed nonconvex optimization by exchanging information between agents to minimize the average of local nonconvex cost functions. The communication channel between agents is normally constrained by limited bandwidth, and the gradient information is typically unavailable. To overcome these limitations, we propose a quantized distributed zeroth-order algorithm, which integrates the deterministic gradient estimator, the standard uniform quantizer, and the distributed gradient tracking algorithm. We establish linear convergence to a global optimal point for the proposed algorithm by assuming Polyak-Lojasiewicz condition for the global cost function and smoothness condition for the local cost functions. Moreover, the proposed algorithm maintains linear convergence at low-data rates with a proper selection of algorithm parameters. Numerical simulations validate the theoretical results.
Keywords:
Cost function
Standards
Convergence
Vectors
Quantization (signal)
Distributed algorithms
Deep learning
Gradient tracking algorithm
linear convergence
nonconvex optimization
uniform quantizer
zeroth-order algorithm
Journal
IF:
10.5
Papers:
1.1W
Citations:
5.0W