arXiv AI

Complexity Induction: Compositional Generalization via Structured Label Distortion

arXiv AI
Aug 28

Complexity Induction: Compositional Generalization via Structured Training Distortion

The paper introduces "complexity induction," a method that distorts training data in a structured way to promote compositional generalization in a standard CNN without changing its architecture. Using synthetic images of colored geometric shapes, the authors encode classes as flat string labels (e.g., "red‑circle") and deliberately omit certain color‑shape combinations from training. Two distortion techniques—mixed labels (soft target distributions based on Jaccard similarity) and expanded dataset (false samples with incorrect labels)—both enable the model to predict unseen class combinations, with mixed labels leveraging the CNN’s embedding structure and expanded training improving embedding factorization. A control experiment with random false labels shows that the effect relies on the structured nature of the distortion rather than noise alone.

By Aleksandr V. Abramov
arXiv Machine Learning
Jul 30

The Advantage of Fine-Grained Training

arXiv:2509. 05130v2 Announce Type: replace Abstract: In classification problems, models are trained to predict a class label based on the input data features.

By Davide Pirovano, Federico Milanesio, Michele Caselle, Piero Fariselli, Matteo Osella
Hugging Face Trending Papers
Jun 22

Sublinearly Structured Deep Neural Networks Achieve Feature Learning Consistency for Compositional Functions

Over the past decade, deep neural networks (DNNs) have achieved remarkable success on complex machine-learning tasks, yet the theoretical foundations of their performance remain incomplete. From a statistical viewpoint, a natural question is: can DNNs attain feature-learning and prediction consistency comparable to that of classical models?

arXiv Machine Learning
6d ago

Deep Learning as Neural Low-Degree Filtering: A Spectral Theory of Hierarchical Feature Learning

The paper introduces Neural Low-Degree Filtering (Neural LoFi), a stylized limit of gradient-based training that turns hierarchical feature learning into an explicit iterative spectral procedure. In this framework, each layer independently selects directions with maximal low-degree correlation to the label, providing a tractable surrogate for deep learning and a kernel-space interpretation. Experiments on fully connected and convolutional networks show that Neural LoFi outperforms lazy random-feature baselines, recovers meaningful structured filters, and aligns with early gradient-descent feature discovery on real datasets.

By Yatin Dandi, Matteo Vilucchio, Luca Arnaboldi, Hugo Tabanelli, Florent Krzakala