# DNCs Require More Planning Steps

arXiv: https://arxiv.org/abs/2406.02187 · HTML: https://mlsanity.com/paper/2406.02187/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 23 references that are in the map.
- First posted on arXiv 4 Jun 2024.

## Builds on (most cited first, 12 of 12)

- [Competition-Level Code Generation with AlphaCode](https://mlsanity.com/paper/2203.07814/) (2022)
- [Neural Turing Machines](https://mlsanity.com/paper/1410.5401/) (2014)
- [Adaptive Computation Time for Recurrent Neural Networks](https://mlsanity.com/paper/1603.08983/) (2016)
- [DiffusionDB: A Large-scale Prompt Gallery Dataset for Text-to-Image Generative Models](https://mlsanity.com/paper/2210.14896/) (2022)
- [Adaptive Neural Networks for Efficient Inference](https://mlsanity.com/paper/1702.07811/) (2017)
- [Neural Random-Access Machines](https://mlsanity.com/paper/1511.06392/) (2015)
- [Scaling Memory-Augmented Neural Networks with Sparse Reads and Writes](https://mlsanity.com/paper/1610.09027/) (2016)
- [MEMO: A Deep Network for Flexible Combination of Episodic Memories](https://mlsanity.com/paper/2001.10913/) (2020)
- [Improving Differentiable Neural Computers Through Memory Masking, De-allocation, and Link Distribution Sharpness Control](https://mlsanity.com/paper/1904.10278/) (2019)
- [Evolutionary Training and Abstraction Yields Algorithmic Generalization of Neural Computers](https://mlsanity.com/paper/2105.07957/) (2021)
- [Robust and Scalable Differentiable Neural Computer for Question Answering](https://mlsanity.com/paper/1807.02658/) (2018)
- [State-Space Constraints Can Improve the Generalisation of the Differentiable Neural Computer to Input Sequences With Unseen Length](https://mlsanity.com/paper/2110.09138/) (2021)

## Abstract (arXiv)

Many recent works use machine learning models to solve various complex algorithmic problems. However, these models attempt to reach a solution without considering the problem's required computational complexity, which can be detrimental to their ability to solve it correctly. In this work we investigate the effect of computational time and memory on generalization of implicit algorithmic solvers. To do so, we focus on the Differentiable Neural Computer (DNC), a general problem solver that also lets us reason directly about its usage of time and memory. In this work, we argue that the number of planning steps the model is allowed to take, which we call "planning budget", is a constraint that can cause the model to generalize poorly and hurt its ability to fully utilize its external memory. We evaluate our method on Graph Shortest Path, Convex Hull, Graph MinCut and Associative Recall, and show how the planning budget can drastically change the behavior of the learned algorithm, in terms of learned time complexity, training time, stability and generalization to inputs larger than those seen during training.