# Neural Generalization of Multiple Kernel Learning

arXiv: https://arxiv.org/abs/2102.13337 · HTML: https://mlsanity.com/paper/2102.13337/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 51 references that are in the map.
- First posted on arXiv 26 Feb 2021.

## Builds on (most cited first, 11 of 11)

- [Neural Tangent Kernel: Convergence and Generalization in Neural Networks](https://mlsanity.com/paper/1806.07572/) (2018)
- [Deep Neural Networks as Gaussian Processes](https://mlsanity.com/paper/1711.00165/) (2017)
- [Deep Kernel Learning](https://mlsanity.com/paper/1511.02222/) (2015)
- [To understand deep learning we need to understand kernel learning](https://mlsanity.com/paper/1802.01396/) (2018)
- [Toward Deeper Understanding of Neural Networks: The Power of Initialization and a Dual View on Expressivity](https://mlsanity.com/paper/1602.05897/) (2016)
- [Convolutional Kernel Networks](https://mlsanity.com/paper/1406.3332/) (2014)
- [Steps Toward Deep Kernel Methods from Infinite Neural Networks](https://mlsanity.com/paper/1508.05133/) (2015)
- [End-to-End Kernel Learning with Supervised Convolutional Kernel Networks](https://mlsanity.com/paper/1605.06265/) (2016)
- [To go deep or wide in learning?](https://mlsanity.com/paper/1402.5634/) (2014)
- [Optimizing Kernel Machines using Deep Learning](https://mlsanity.com/paper/1711.05374/) (2017)
- [Totally Deep Support Vector Machines](https://mlsanity.com/paper/1912.05864/) (2019)

## Abstract (arXiv)

Multiple Kernel Learning is a conventional way to learn the kernel function in kernel-based methods. MKL algorithms enhance the performance of kernel methods. However, these methods have a lower complexity compared to deep learning models and are inferior to these models in terms of recognition accuracy. Deep learning models can learn complex functions by applying nonlinear transformations to data through several layers. In this paper, we show that a typical MKL algorithm can be interpreted as a one-layer neural network with linear activation functions. By this interpretation, we propose a Neural Generalization of Multiple Kernel Learning (NGMKL), which extends the conventional multiple kernel learning framework to a multi-layer neural network with nonlinear activation functions. Our experiments on several benchmarks show that the proposed method improves the complexity of MKL algorithms and leads to higher recognition accuracy.