# Efficient Second-Order Neural Network Optimization via Adaptive Trust Region Methods

arXiv: https://arxiv.org/abs/2410.02293 · HTML: https://mlsanity.com/paper/2410.02293/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 6 references that are in the map.
- First posted on arXiv 3 Oct 2024.

## Builds on (most cited first, 5 of 5)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection](https://mlsanity.com/paper/2403.03507/) (2024)
- [Worst-Case Complexity of an SQP Method for Nonlinear Equality Constrained Stochastic Optimization](https://mlsanity.com/paper/2112.14799/) (2021)
- [Hessian Averaging in Stochastic Newton Methods Achieves Superlinear Convergence](https://mlsanity.com/paper/2204.09266/) (2022)
- [A consistently adaptive trust-region method](https://mlsanity.com/paper/2408.01874/) (2024)

## Built on by (most cited first, 1 of 1)

- [Evolution of Optimization Methods: Algorithms, Scenarios, and Evaluations](https://mlsanity.com/paper/2604.12968/) (2026)

## Abstract (arXiv)

Second-order optimization methods offer notable advantages in training deep neural networks by utilizing curvature information to achieve faster convergence. However, traditional second-order techniques are computationally prohibitive, primarily due to the large matrix inversions and high memory demands they require. While adaptive trust-region methods have been developed to mitigate these issues, their performance is often hindered by conservative estimates of key parameters, such as the Lipschitz constant of the Hessian, resulting in suboptimal outcomes. In this paper, we introduce SecondOrderAdaptiveAdam (SOAA), a novel optimization algorithm designed to overcome these limitations. SOAA approximates the Fisher information matrix using a diagonal representation, reducing computational complexity from (O(n2)) to (O(n)), thereby making it suitable for large-scale deep learning models, including large language models (LLMs). Additionally, the algorithm integrates an adaptive trust-region mechanism that dynamically adjusts the trust region size based on observed loss reduction, ensuring both robust convergence and computational efficiency. We empirically demonstrate that SOAA achieves faster and more stable convergence compared to first-order optimizers, such as Adam, under similar computational constraints. However, the diagonal approximation of the Fisher information matrix may be less effective in capturing higher-order interactions between gradients, suggesting potential areas for further refinement and future research.