# Linear Response Estimators for Singular Statistical Models

arXiv: https://arxiv.org/abs/2605.07970 · HTML: https://mlsanity.com/paper/2605.07970/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 23 references that are in the map.
- First posted on arXiv 8 May 2026.

## Builds on (most cited first, 7 of 7)

- [Understanding Black-box Predictions via Influence Functions](https://mlsanity.com/paper/1703.04730/) (2017)
- [Covariances, Robustness, and Variational Bayes](https://mlsanity.com/paper/1709.02536/) (2017)
- [Differentiation and Specialization of Attention Heads via the Refined Local Learning Coefficient](https://mlsanity.com/paper/2410.02984/) (2024)
- [Bayesian Influence Functions for Hessian-Free Data Attribution](https://mlsanity.com/paper/2509.26544/) (2025)
- [Structural Inference: Interpreting Small Language Models with Susceptibilities](https://mlsanity.com/paper/2504.18274/) (2025)
- [Patterning: The Dual of Interpretability](https://mlsanity.com/paper/2601.13548/) (2026)
- [From Global to Local: A Scalable Benchmark for Local Posterior Sampling](https://mlsanity.com/paper/2507.21449/) (2025)

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

- [Patterning in Practice: Debiasing Reward Models with Susceptibilities](https://mlsanity.com/paper/2609.00699/) (2026)

## Abstract (arXiv)

We define susceptibilities as a measure of the response of an observable quantity of a parameterized statistical model to a perturbation of the data for a general class of observables. We define estimators for these susceptibilities as statistics in a sequence of n data-points and prove that these estimators are consistent and asymptotically unbiased in the large n regime.