# Double Descent as a Lens for Sample Efficiency in Autoregressive vs. Discrete Diffusion Models

arXiv: https://arxiv.org/abs/2509.24974 · HTML: https://mlsanity.com/paper/2509.24974/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Discrete and text diffusion, one of 14 directions in Diffusion models.
- Builds on 13 of its 16 references that are in the map.
- First posted on arXiv 29 Sep 2025.

## Placed in

- Diffusion models / [Discrete and text diffusion](https://mlsanity.com/diffusion/discrete-and-text-diffusion/)

## Builds on (most cited first, 13 of 13)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Structured Denoising Diffusion Models in Discrete State-Spaces](https://mlsanity.com/paper/2107.03006/) (2021)
- [Reconciling modern machine learning practice and the bias-variance trade-off](https://mlsanity.com/paper/1812.11118/) (2018)
- [Deep Double Descent: Where Bigger Models and More Data Hurt](https://mlsanity.com/paper/1912.02292/) (2019)
- [The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A"](https://mlsanity.com/paper/2309.12288/) (2023)
- [Will we run out of data? Limits of LLM scaling based on human-generated data](https://mlsanity.com/paper/2211.04325/) (2022)
- [Physics of Language Models: Part 3.2, Knowledge Manipulation](https://mlsanity.com/paper/2309.14402/) (2023)
- [Diffusion Beats Autoregressive in Data-Constrained Settings](https://mlsanity.com/paper/2507.15857/) (2025)
- [The Factorization Curse: Which Tokens You Predict Underlie the Reversal Curse and More](https://mlsanity.com/paper/2406.05183/) (2024)
- [Double Descent Optimization Pattern and Aliasing: Caveats of Noisy Labels](https://mlsanity.com/paper/2106.02100/) (2021)

## Built on by (most cited first, 1 of 1)

- [Spherical Boltzmann machines: a solvable theory of learning and generation in energy-based models](https://mlsanity.com/paper/2605.09031/) (2026)

## Abstract (arXiv)

Data scarcity drives the need for more sample-efficient large language models. In this work, we use the double descent phenomenon to holistically compare the sample efficiency of discrete diffusion and autoregressive models. We show that discrete diffusion models require larger capacity and more training epochs to escape their underparameterized regime and reach the interpolation threshold. In the strongly overparameterized regime, both models exhibit similar behavior, with neither exhibiting a pronounced second descent in test loss across a large range of model sizes. Overall, our results indicate that autoregressive models are more sample-efficient on small-scale datasets, while discrete diffusion models only become competitive when given sufficient capacity and compute.