# On the ε-Free Inference Complexity of Absorbing Discrete Diffusion

arXiv: https://arxiv.org/abs/2509.21835 · HTML: https://mlsanity.com/paper/2509.21835/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models.
- Builds on 19 of its 23 references that are in the map.
- First posted on arXiv 26 Sep 2025.

## Placed in

- Diffusion models / [Diffusion foundations and sampling](https://mlsanity.com/diffusion/diffusion-foundations-and-sampling/)

## Builds on (most cited first, 19 of 19)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [Structured Denoising Diffusion Models in Discrete State-Spaces](https://mlsanity.com/paper/2107.03006/) (2021)
- [Large Language Diffusion Models](https://mlsanity.com/paper/2502.09992/) (2025)
- [Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution](https://mlsanity.com/paper/2310.16834/) (2023)
- [A Continuous Time Framework for Discrete Denoising Models](https://mlsanity.com/paper/2205.14987/) (2022)
- [Sampling is as easy as learning the score: theory for diffusion models with minimal data assumptions](https://mlsanity.com/paper/2209.11215/) (2022)
- [Your Absorbing Discrete Diffusion Secretly Models the Conditional Distributions of Clean Data](https://mlsanity.com/paper/2406.03736/) (2024)
- [Train for the Worst, Plan for the Best: Understanding Token Ordering in Masked Diffusions](https://mlsanity.com/paper/2502.06768/) (2025)
- [Autoregressive Diffusion Models](https://mlsanity.com/paper/2110.02037/) (2021)
- [Masked Diffusion Models are Secretly Time-Agnostic Masked Models and Exploit Inaccurate Categorical Sampling](https://mlsanity.com/paper/2409.02908/) (2024)
- [From Denoising Diffusions to Denoising Markov Models](https://mlsanity.com/paper/2211.03595/) (2022)
- [How Discrete and Continuous Diffusion Meet: Comprehensive Analysis of Discrete Diffusion Models via a Stochastic Integral Framework](https://mlsanity.com/paper/2410.03601/) (2024)
- [Convergence Analysis of Discrete Diffusion Model: Exact Implementation through Uniformization](https://mlsanity.com/paper/2402.08095/) (2024)
- [Convergence of Score-Based Discrete Diffusion Models: A Discrete-Time Analysis](https://mlsanity.com/paper/2410.02321/) (2024)
- [Absorb and Converge: Provable Convergence Guarantee for Absorbing Discrete Diffusion Models](https://mlsanity.com/paper/2506.02318/) (2025)
- [Almost Linear Convergence under Minimal Score Assumptions: Quantized Transition Diffusion](https://mlsanity.com/paper/2505.21892/) (2025)

## Abstract (arXiv)

Absorbing discrete diffusion has emerged as a dominant framework for discrete data generation. However, a significant disparity remains between its empirical success and theoretical understanding: existing analyses fail to demonstrate a complexity advantage over the O(d ln(d/ε)) baseline established for uniform discrete diffusion. We bridge this gap by identifying a critical structural advantage: whereas uniform diffusion redundantly re-denoises valid elements, the absorbing scheme denoises each absorbing state exactly once. Leveraging this insight, we introduce Absorbing-Aware Truncated Uniformization (AATU). We prove that AATU achieves ε-TV convergence with O(d ln d) complexity-independent of the error tolerance ε-thereby strictly outperforming existing uniform baselines. Beyond improving convergence rates, our analysis eliminates the restrictive bounded-score assumption commonly required in prior studies of uniformization-based inference. Furthermore, we extend AATU to time-invariant parameterizations, showing that it naturally adopts an imputation-type inference with a uniformly randomized denoising order. When combined with a lazy update strategy, TV convergence requires only O(d) discrete score evaluations. These results not only establish a rigorous foundation for absorbing discrete diffusion -- confirming its efficiency in high-accuracy generation -- but also open new avenues for analyzing diffusion-based language models under the masking paradigm.