# Exact Scaling Laws for a Random-Features Bigram Model

arXiv: https://arxiv.org/abs/2610.19281 · HTML: https://mlsanity.com/paper/2610.19281/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 16 references that are in the map.
- First posted on arXiv 13 Oct 2026.

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

- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [The Pile: An 800GB Dataset of Diverse Text for Language Modeling](https://mlsanity.com/paper/2101.00027/) (2020)
- [Explaining Neural Scaling Laws](https://mlsanity.com/paper/2102.06701/) (2021)
- [The Quantization Model of Neural Scaling](https://mlsanity.com/paper/2303.13506/) (2023)
- [A Tale of Tails: Model Collapse as a Change of Scaling Laws](https://mlsanity.com/paper/2402.07043/) (2024)
- [A Solvable Model of Neural Scaling Laws](https://mlsanity.com/paper/2210.16859/) (2022)
- [Generalization Error Rates in Kernel Regression: The Crossover from the Noiseless to Noisy Regime](https://mlsanity.com/paper/2105.15004/) (2021)
- [Scaling Laws for Associative Memories](https://mlsanity.com/paper/2310.02984/) (2023)
- [Understanding Transformers via N-gram Statistics](https://mlsanity.com/paper/2407.12034/) (2024)
- [Scaling Laws for Gradient Descent and Sign Descent for Linear Bigram Models under Zipf's Law](https://mlsanity.com/paper/2505.19227/) (2025)
- [An exactly solvable model for emergence and scaling laws in the multitask sparse parity problem](https://mlsanity.com/paper/2404.17563/) (2024)

## Abstract (arXiv)

Understanding neural scaling laws is increasingly important for theory and practice, yet first-principles explanations remain limited even in simple settings. In this work, we study capacity-limited scaling in a bottlenecked bigram model with power-law (Zipf) token statistics, viewed as an analytically tractable toy model of a large language model. Fixed random embeddings serve as a proxy for representational capacity and induce an explicit bottleneck of width, allowing us to derive scaling laws for prediction regret as a function of model width, vocabulary size, and the Zipf exponent. Our results complement recent theoretical accounts based on optimization dynamics by isolating scaling due purely to representational constraints. In the appropriate regime, the theory recovers the functional form of classical neural scaling laws and suggests that heavy-tailed language statistics may underlie both optimization- and capacity-driven scaling. Experiments natural language datasets (WikiText2, OpenWebText) closely match the predicted curves.