# Interpolated-MLPs: Controllable Inductive Bias

arXiv: https://arxiv.org/abs/2410.09655 · HTML: https://mlsanity.com/paper/2410.09655/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 9 references that are in the map.
- First posted on arXiv 12 Oct 2024.

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

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [MLP-Mixer: An all-MLP Architecture for Vision](https://mlsanity.com/paper/2105.01601/) (2021)
- [Scaling MLPs: A Tale of Inductive Bias](https://mlsanity.com/paper/2306.13575/) (2023)
- [RepMLPNet: Hierarchical Vision MLP with Re-parameterized Locality](https://mlsanity.com/paper/2112.11081/) (2021)

## Abstract (arXiv)

Due to their weak inductive bias, Multi-Layer Perceptrons (MLPs) have subpar performance at low-compute levels compared to standard architectures such as convolution-based networks (CNN). Recent work, however, has shown that the performance gap drastically reduces as the amount of compute is increased without changing the amount of inductive bias. In this work, we study the converse: in the low-compute regime, how does the incremental increase of inductive bias affect performance? To quantify inductive bias, we propose a "soft MLP" approach, which we coin Interpolated MLP (I-MLP). We control the amount of inductive bias in the standard MLP by introducing a novel algorithm based on interpolation between fixed weights from a prior model with high inductive bias. We showcase our method using various prior models, including CNNs and the MLP-Mixer architecture. This interpolation scheme allows fractional control of inductive bias, which may be attractive when full inductive bias is not desired (e.g. in the mid-compute regime). We find experimentally that for Vision Tasks in the low-compute regime, there is a continuous and two-sided logarithmic relationship between inductive bias and performance when using CNN and MLP-Mixer prior models.