# Multi-kernel Passive Stochastic Gradient Algorithms and Transfer Learning

arXiv: https://arxiv.org/abs/2008.10020 · HTML: https://mlsanity.com/paper/2008.10020/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Aug 2020.

## Built on by (most cited first, 3 of 3)

- [Finite-Sample Bounds for Adaptive Inverse Reinforcement Learning using Passive Langevin Dynamics](https://mlsanity.com/paper/2304.09123/) (2023)
- [Estimating the minimizer and the minimum value of a regression function under passive design](https://mlsanity.com/paper/2211.16457/) (2022)
- [Malliavin Calculus with Weak Derivatives for Counterfactual Stochastic Optimization](https://mlsanity.com/paper/2510.00297/) (2025)

## Abstract (arXiv)

This paper develops a novel passive stochastic gradient algorithm. In passive stochastic approximation, the stochastic gradient algorithm does not have control over the location where noisy gradients of the cost function are evaluated. Classical passive stochastic gradient algorithms use a kernel that approximates a Dirac delta to weigh the gradients based on how far they are evaluated from the desired point. In this paper we construct a multi-kernel passive stochastic gradient algorithm. The algorithm performs substantially better in high dimensional problems and incorporates variance reduction. We analyze the weak convergence of the multi-kernel algorithm and its rate of convergence. In numerical examples, we study the multi-kernel version of the passive least mean squares (LMS) algorithm for transfer learning to compare the performance with the classical passive version.