Multi-step Predictive Coding Leads To Simplicity Bias

• URL: http://arxiv.org/abs/2511.09290v1
• Date: Thu, 13 Nov 2025 01:44:41 GMT
• Title: Multi-step Predictive Coding Leads To Simplicity Bias
• Abstract summary: We investigate how the prediction horizon and network depth shape the solutions of predictive coding tasks.<n>We show that sufficiently deep networks trained with multi-step prediction horizons consistently recover the underlying latent structure.<n>Our results provide a principled understanding of when and why predictive coding induces structured representations.
• Score: 2.8933605229876664
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Predictive coding is a framework for understanding the formation of low-dimensional internal representations mirroring the environment's latent structure. The conditions under which such representations emerge remain unclear. In this work, we investigate how the prediction horizon and network depth shape the solutions of predictive coding tasks. Using a minimal abstract setting inspired by prior work, we show empirically and theoretically that sufficiently deep networks trained with multi-step prediction horizons consistently recover the underlying latent structure, a phenomenon explained through the Ordinary Least Squares estimator structure and biases in learning dynamics. We then extend these insights to nonlinear networks and complex datasets, including piecewise linear functions, MNIST, multiple latent states and higher dimensional state geometries. Our results provide a principled understanding of when and why predictive coding induces structured representations, bridging the gap between empirical observations and theoretical foundations.

Related papers

• Uncovering the Latent Potential of Deep Intermediate Representations [16.988545433223933]
  We show that task-relevant information is distributed non-monotonically across layers and cannot be recovered by nave aggregation.<n>We introduce Layer-wise Optimal Embedding Selection (LOES), a constructive spectral method that identifies task-discriminative subspaces.<n>Our method reveals how semantic factors are distributed across layers, thereby enabling cross-lingual and cross-modal interpretability analyses.
  arXiv  Detail & Related papers  (2026-05-21T20:58:42Z)
• Pointwise Generalization in Deep Neural Networks [24.565019622696664]
  We identify the structural properties and mathematical principles that explain the tractability of deep networks.<n>We show that deep networks are mathematically tractable in practical regimes and that their generalization is sharply explained by pointwise, feature-spectrum-aware complexity.
  arXiv  Detail & Related papers  (2026-05-18T16:09:06Z)
• Deep Learning as Neural Low-Degree Filtering: A Spectral Theory of Hierarchical Feature Learning [17.247172396896698]
  We introduce Neural Low-Degree Filtering (Neural LoFi), a stylized limit of gradient-based training in which hierarchical feature learning becomes an explicit iterative spectral procedure.<n>We show that Neural LoFi improves over lazy random-feature baselines, recovers meaningful structured filters, and predicts representations aligned with early gradient-descent feature discovery with real datasets.
  arXiv  Detail & Related papers  (2026-05-13T14:44:06Z)
• Emergent Structured Representations Support Flexible In-Context Inference in Large Language Models [77.98801218316505]
  Large language models (LLMs) exhibit emergent behaviors suggestive of human-like reasoning.<n>We investigate the internal processing of LLMs during in-context concept inference.
  arXiv  Detail & Related papers  (2026-02-08T03:14:39Z)
• Approximating Latent Manifolds in Neural Networks via Vanishing Ideals [20.464009622419766]
  We establish a connection between manifold learning and computational algebra by demonstrating how vanishing ideals can characterize the latent manifold of deep networks.<n>We propose a new neural architecture that truncates a pretrained network at an intermediate layer, and approximates each class manifold via generators of the vanishing ideal.<n>The resulting models have significantly fewer layers than their pretrained baselines, while maintaining comparable accuracy, achieving higher throughput and utilizing fewer parameters.
  arXiv  Detail & Related papers  (2025-02-20T21:23:02Z)
• Deep Learning Through A Telescoping Lens: A Simple Model Provides Empirical Insights On Grokking, Gradient Boosting & Beyond [61.18736646013446]
  In pursuit of a deeper understanding of its surprising behaviors, we investigate the utility of a simple yet accurate model of a trained neural network. Across three case studies, we illustrate how it can be applied to derive new empirical insights on a diverse range of prominent phenomena.
  arXiv  Detail & Related papers  (2024-10-31T22:54:34Z)
• Unifying Low Dimensional Observations in Deep Learning Through the Deep Linear Unconstrained Feature Model [0.0]
  We study low-dimensional structure in the weights, Hessian's, gradients, and feature vectors of deep neural networks. We show how they can be unified within a generalized unconstrained feature model.
  arXiv  Detail & Related papers  (2024-04-09T08:17:32Z)
• Rank Diminishing in Deep Neural Networks [71.03777954670323]
  Rank of neural networks measures information flowing across layers. It is an instance of a key structural condition that applies across broad domains of machine learning. For neural networks, however, the intrinsic mechanism that yields low-rank structures remains vague and unclear.
  arXiv  Detail & Related papers  (2022-06-13T12:03:32Z)
• Analytic Insights into Structure and Rank of Neural Network Hessian Maps [32.90143789616052]
  Hessian of a neural network captures parameter interactions through second-order derivatives of the loss. We develop theoretical tools to analyze the range of the Hessian map, providing us with a precise understanding of its rank deficiency. This yields exact formulas and tight upper bounds for the Hessian rank of deep linear networks.
  arXiv  Detail & Related papers  (2021-06-30T17:29:58Z)
• What can linearized neural networks actually say about generalization? [67.83999394554621]
  In certain infinitely-wide neural networks, the neural tangent kernel (NTK) theory fully characterizes generalization. We show that the linear approximations can indeed rank the learning complexity of certain tasks for neural networks. Our work provides concrete examples of novel deep learning phenomena which can inspire future theoretical research.
  arXiv  Detail & Related papers  (2021-06-12T13:05:11Z)
• A neural anisotropic view of underspecification in deep learning [60.119023683371736]
  We show that the way neural networks handle the underspecification of problems is highly dependent on the data representation. Our results highlight that understanding the architectural inductive bias in deep learning is fundamental to address the fairness, robustness, and generalization of these systems.
  arXiv  Detail & Related papers  (2021-04-29T14:31:09Z)
• A Chain Graph Interpretation of Real-World Neural Networks [58.78692706974121]
  We propose an alternative interpretation that identifies NNs as chain graphs (CGs) and feed-forward as an approximate inference procedure. The CG interpretation specifies the nature of each NN component within the rich theoretical framework of probabilistic graphical models. We demonstrate with concrete examples that the CG interpretation can provide novel theoretical support and insights for various NN techniques.
  arXiv  Detail & Related papers  (2020-06-30T14:46:08Z)
• Investigating the Compositional Structure Of Deep Neural Networks [1.8899300124593645]
  We introduce a novel theoretical framework based on the compositional structure of piecewise linear activation functions. It is possible to characterize the instances of the input data with respect to both the predicted label and the specific (linear) transformation used to perform predictions. Preliminary tests on the MNIST dataset show that our method can group input instances with regard to their similarity in the internal representation of the neural network.
  arXiv  Detail & Related papers  (2020-02-17T14:16:17Z)
• Understanding Generalization in Deep Learning via Tensor Methods [53.808840694241]
  We advance the understanding of the relations between the network's architecture and its generalizability from the compression perspective. We propose a series of intuitive, data-dependent and easily-measurable properties that tightly characterize the compressibility and generalizability of neural networks.
  arXiv  Detail & Related papers  (2020-01-14T22:26:57Z)

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.