.png){kind=icon}
Return
Mirror descent algorithm for stochastic multi-objective optimization and its application to machine learning
.png){kind=icon}
PRE
AI
DOI：10.1007/s10589-026-00796-y.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Stochastic multi-objective optimization (SMOO) has attracted increasing interest as a framework for machine learning problems with multiple objectives. The nonlinearity of the subproblem solution mapping introduces bias in the weighting parameters, which complicates the convergence analysis of multi-gradient algorithms. In this paper, we propose the Multi-gradient Stochastic Mirror Descent (MSMD) algorithm, which solves the SMOO subproblem via the stochastic mirror descent method and provides convergence guarantees. By selecting an appropriate Bregman distance-generating function, the algorithm admits a closed-form solution for the weighting vector and requires only a single stochastic gradient sample per iteration. We establish sublinear convergence rates for MSMD under four combinations of inner and outer step size strategies. A variant of MSMD for SMOO with preferences is also proposed and analyzed. Numerical experiments on benchmark test functions and neural network training tasks show that MSMD achieves competitive performance.
Keywords:
Stochastic multi-objective optimization
Stochastic mirror descent algorithm
Multi-gradient descent algorithm
Convergence rate
Journal
C
IF:
2
Papers:
74
Citations:
3.5K
Organization
Cited Papers
No cited papers available