# Eigen Memory Trees

arXiv: https://arxiv.org/abs/2210.14077 · HTML: https://mlsanity.com/paper/2210.14077/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 37 references that are in the map.
- First posted on arXiv 25 Oct 2022.

## Builds on (most cited first, 14 of 14)

- [OpenML: networked science in machine learning](https://mlsanity.com/paper/1407.7722/) (2014)
- [Online Learning: A Comprehensive Survey](https://mlsanity.com/paper/1802.02871/) (2018)
- [Neural Episodic Control](https://mlsanity.com/paper/1703.01988/) (2017)
- [Model-Free Episodic Control](https://mlsanity.com/paper/1606.04460/) (2016)
- [Corralling a Band of Bandit Algorithms](https://mlsanity.com/paper/1612.06246/) (2016)
- [How Complex is your classification problem? A survey on measuring classification complexity](https://mlsanity.com/paper/1808.03591/) (2018)
- [A Contextual Bandit Bake-off](https://mlsanity.com/paper/1802.04064/) (2018)
- [Episodic Memory Deep Q-Networks](https://mlsanity.com/paper/1805.07603/) (2018)
- [Robust High-dimensional Memory-augmented Neural Networks](https://mlsanity.com/paper/2010.01939/) (2020)
- [The Fast Convergence of Incremental PCA](https://mlsanity.com/paper/1501.03796/) (2015)
- [Fast deep reinforcement learning using online adjustments from the past](https://mlsanity.com/paper/1810.08163/) (2018)
- [Randomized partition trees for exact nearest neighbor search](https://mlsanity.com/paper/1302.1948/) (2013)
- [Memory-augmented Neural Machine Translation](https://mlsanity.com/paper/1708.02005/) (2017)
- [Contextual Memory Trees](https://mlsanity.com/paper/1807.06473/) (2018)

## Abstract (arXiv)

This work introduces the Eigen Memory Tree (EMT), a novel online memory model for sequential learning scenarios. EMTs store data at the leaves of a binary tree and route new samples through the structure using the principal components of previous experiences, facilitating efficient (logarithmic) access to relevant memories. We demonstrate that EMT outperforms existing online memory approaches, and provide a hybridized EMT-parametric algorithm that enjoys drastically improved performance over purely parametric methods with nearly no downsides. Our findings are validated using 206 datasets from the OpenML repository in both bounded and infinite memory budget situations.