Patterning: The Dual of Interpretability

• URL: http://arxiv.org/abs/2601.13548v1
• Date: Tue, 20 Jan 2026 03:15:27 GMT
• Title: Patterning: The Dual of Interpretability
• Authors: George Wang, Daniel Murfet,
• Abstract summary: We show that patterning can select which algorithm the model learns by targeting the local learning coefficient of each solution.<n>Results establish that the same mathematical framework used to read internal structure can be inverted to write it.
• Score: 2.3443925855637073
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Mechanistic interpretability aims to understand how neural networks generalize beyond their training data by reverse-engineering their internal structures. We introduce patterning as the dual problem: given a desired form of generalization, determine what training data produces it. Our approach is based on susceptibilities, which measure how posterior expectation values of observables respond to infinitesimal shifts in the data distribution. Inverting this linear response relationship yields the data intervention that steers the model toward a target internal configuration. We demonstrate patterning in a small language model, showing that re-weighting training data along principal susceptibility directions can accelerate or delay the formation of structure, such as the induction circuit. In a synthetic parentheses balancing task where multiple algorithms achieve perfect training accuracy, we show that patterning can select which algorithm the model learns by targeting the local learning coefficient of each solution. These results establish that the same mathematical framework used to read internal structure can be inverted to write it.

Related papers

• Neural Network Reprogrammability: A Unified Theme on Model Reprogramming, Prompt Tuning, and Prompt Instruction [57.19302613163439]
  We introduce neural network reprogrammability as a unifying framework for model adaptation.<n>We present a taxonomy that categorizes such information manipulation approaches across four key dimensions.<n>We also analyze remaining technical challenges and ethical considerations.
  arXiv  Detail & Related papers  (2025-06-05T05:42:27Z)
• Learning where to learn: Training data distribution optimization for scientific machine learning [4.726397480637032]
  In scientific machine learning, models are routinely deployed with parameter values or boundary conditions far from those used in training.<n>This paper studies the learning-where-to-learn problem of designing a training data distribution that minimizes average prediction error.
  arXiv  Detail & Related papers  (2025-05-27T18:00:58Z)
• Distilled Datamodel with Reverse Gradient Matching [74.75248610868685]
  We introduce an efficient framework for assessing data impact, comprising offline training and online evaluation stages. Our proposed method achieves comparable model behavior evaluation while significantly speeding up the process compared to the direct retraining method.
  arXiv  Detail & Related papers  (2024-04-22T09:16:14Z)
• On Linearizing Structured Data in Encoder-Decoder Language Models: Insights from Text-to-SQL [8.57550491437633]
  This work investigates the linear handling of structured data in encoder-decoder language models, specifically T5. Our findings reveal the model's ability to mimic human-designed processes such as schema linking and syntax prediction. We also uncover insights into the model's internal mechanisms, including the ego-centric nature of structure node encodings.
  arXiv  Detail & Related papers  (2024-04-03T01:16:20Z)
• A Recursively Recurrent Neural Network (R2N2) Architecture for Learning Iterative Algorithms [64.3064050603721]
  We generalize Runge-Kutta neural network to a recurrent neural network (R2N2) superstructure for the design of customized iterative algorithms. We demonstrate that regular training of the weight parameters inside the proposed superstructure on input/output data of various computational problem classes yields similar iterations to Krylov solvers for linear equation systems, Newton-Krylov solvers for nonlinear equation systems, and Runge-Kutta solvers for ordinary differential equations.
  arXiv  Detail & Related papers  (2022-11-22T16:30:33Z)
• Amortized Inference for Causal Structure Learning [72.84105256353801]
  Learning causal structure poses a search problem that typically involves evaluating structures using a score or independence test. We train a variational inference model to predict the causal structure from observational/interventional data. Our models exhibit robust generalization capabilities under substantial distribution shift.
  arXiv  Detail & Related papers  (2022-05-25T17:37:08Z)
• Data-driven emergence of convolutional structure in neural networks [83.4920717252233]
  We show how fully-connected neural networks solving a discrimination task can learn a convolutional structure directly from their inputs. By carefully designing data models, we show that the emergence of this pattern is triggered by the non-Gaussian, higher-order local structure of the inputs.
  arXiv  Detail & Related papers  (2022-02-01T17:11:13Z)
• Dynamic Inference with Neural Interpreters [72.90231306252007]
  We present Neural Interpreters, an architecture that factorizes inference in a self-attention network as a system of modules. inputs to the model are routed through a sequence of functions in a way that is end-to-end learned. We show that Neural Interpreters perform on par with the vision transformer using fewer parameters, while being transferrable to a new task in a sample efficient manner.
  arXiv  Detail & Related papers  (2021-10-12T23:22:45Z)
• Relative gradient optimization of the Jacobian term in unsupervised deep learning [9.385902422987677]
  Learning expressive probabilistic models correctly describing the data is a ubiquitous problem in machine learning. Deep density models have been widely used for this task, but their maximum likelihood based training requires estimating the log-determinant of the Jacobian. We propose a new approach for exact training of such neural networks.
  arXiv  Detail & Related papers  (2020-06-26T16:41:08Z)
• Embodied Self-supervised Learning by Coordinated Sampling and Training [14.107020105091662]
  We propose a novel self-supervised approach to solve inverse problems by employing the corresponding physical forward process. The proposed approach works in an analysis-by-synthesis manner to learn an inference network by iteratively sampling and training. We prove the feasibility of the proposed method by tackling the acoustic-to-articulatory inversion problem to infer articulatory information from speech.
  arXiv  Detail & Related papers  (2020-06-20T14:05:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.