# A Convexity-dependent Two-Phase Training Algorithm for Deep Neural Networks

arXiv: https://arxiv.org/abs/2510.25366 · HTML: https://mlsanity.com/paper/2510.25366/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 21 references that are in the map.
- First posted on arXiv 29 Oct 2025.

## Builds on (most cited first, 8 of 8)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima](https://mlsanity.com/paper/1609.04836/) (2016)
- [Towards Practical Adam: Non-Convexity, Convergence Theory, and Mini-Batch Acceleration](https://mlsanity.com/paper/2101.05471/) (2021)
- [The Convex Landscape of Neural Networks: Characterizing Global Optima and Stationary Points via Lasso Models](https://mlsanity.com/paper/2312.12657/) (2023)
- [Review Non-convex Optimization Method for Machine Learning](https://mlsanity.com/paper/2410.02017/) (2024)
- [Reducing the Transformer Architecture to a Minimum](https://mlsanity.com/paper/2410.13732/) (2024)

## Abstract (arXiv)

The key task of machine learning is to minimize the loss function that measures the model fit to the training data. The numerical methods to do this efficiently depend on the properties of the loss function. The most decisive among these properties is the convexity or non-convexity of the loss function. The fact that the loss function can have, and frequently has, non-convex regions has led to a widespread commitment to non-convex methods such as Adam. However, a local minimum implies that, in some environment around it, the function is convex. In this environment, second-order minimizing methods such as the Conjugate Gradient (CG) give a guaranteed superlinear convergence. We propose a novel framework grounded in the hypothesis that loss functions in real-world tasks swap from initial non-convexity to convexity towards the optimum. This is a property we leverage to design an innovative two-phase optimization algorithm. The presented algorithm detects the swap point by observing the gradient norm dependence on the loss. In these regions, non-convex (Adam) and convex (CG) algorithms are used, respectively. Computing experiments confirm the hypothesis that this simple convexity structure is frequent enough to be practically exploited to substantially improve convergence and accuracy.