# Guided Learning of Nonconvex Models through Successive Functional Gradient Optimization

arXiv: https://arxiv.org/abs/2006.16840 · HTML: https://mlsanity.com/paper/2006.16840/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Jun 2020.

## Built on by (most cited first, 7 of 7)

- [A general class of surrogate functions for stable and efficient reinforcement learning](https://mlsanity.com/paper/2108.05828/) (2021)
- [LocoProp: Enhancing BackProp via Local Loss Optimization](https://mlsanity.com/paper/2106.06199/) (2021)
- [Inconsistency, Instability, and Generalization Gap of Deep Neural Network Training](https://mlsanity.com/paper/2306.00169/) (2023)
- [Target-based Surrogates for Stochastic Optimization](https://mlsanity.com/paper/2302.02607/) (2023)
- [Solving Hidden Monotone Variational Inequalities with Surrogate Losses](https://mlsanity.com/paper/2411.05228/) (2024)
- [A Framework of Meta Functional Learning for Regularising Knowledge Transfer](https://mlsanity.com/paper/2203.14840/) (2022)
- [Acceleration in Policy Optimization](https://mlsanity.com/paper/2306.10587/) (2023)

## Abstract (arXiv)

This paper presents a framework of successive functional gradient optimization for training nonconvex models such as neural networks, where training is driven by mirror descent in a function space. We provide a theoretical analysis and empirical study of the training method derived from this framework. It is shown that the method leads to better performance than that of standard training techniques.