paper-with-me

홈 › Papers

Representation Gap: Explaining the Unreasonable Effectiveness of Neural Networks from a Geometric Perspective

2026-05-20 · David Perera, Victor Moura, Lais Isabelle Alves dos Santos, Michel F. C. Haddad, Flavio Figueiredo arxiv

Characterizing precisely the asymptotic generalization error of neural networks using parameters that can be estimated efficiently is a crucial problem in machine learning, which relies heavily on heuristics and practitioners' intuition to make key design choices. In order to mitigate this issue, we introduce the Representation Gap, a metric closely related to the generalization error, but admitting better-behaved asymptotic dynamics. Focusing on equivariant diffusion models and leveraging results from optimal quantization and point-process theory, we derive a precise asymptotic equivalent of the Representation Gap and show that it is governed by a single parameter, the \textit{intrinsic dimension} of the task, which is easy to interpret, efficient to estimate, and can be linked to the equivariances of common neural network architectures. We show that this asymptotic dynamic also extends to a broader range of tasks and training algorithms. Finally, we demonstrate empirically that our asymptotic law and intrinsic dimension estimation are accurate on a wide range of synthetic datasets, where these quantities are known, as well as on more realistic datasets, where we obtain results consistent with the related literature.

📄 PDF Abstract BibTeX arXiv:2605.21692

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

The Unreasonable Effectiveness of Structured Random Orthogonal Embeddings

2017-03-02 · NeurIPS 2017 12 · Krzysztof Choromanski, Mark Rowland, Adrian Weller

We examine a class of embeddings based on structured random matrices with orthogonal rows which can be applied in many machine learning applications including dimensionality reduction and kernel approximation. For both t…

BIG-bench Machine LearningDimensionality Reduction

The Unreasonable Effectiveness of Word Representations for Twitter Named Entity Recognition

2015-05-01 · HLT 2015 5 · Colin Cherry, Hongyu Guo
Domain AdaptationEntity Linkingnamed-entity-recognitionNamed Entity Recognition+3

Emergent Causal-Geometric Dynamics Across Depth in Large Language Models

2026-02-04 · Shahar Haim, Daniel C McNamee arxiv

Geometric analyses of large language model (LLM) representations reveal structured variation across depth but remain fundamentally correlational with respect to token prediction formation. Meanwhile, causal interventions…

Radius-margin bounds for deep neural networks

2018-11-03 · Mayank Sharma, Jayadeva, Sumit Soman

Explaining the unreasonable effectiveness of deep learning has eluded researchers around the globe. Various authors have described multiple metrics to evaluate the capacity of deep architectures. In this paper, we allude…

Can I Trust the Explainer? Verifying Post-hoc Explanatory Methods

2019-10-04 · Oana-Maria Camburu, Eleonora Giunchiglia, Jakob Foerster, Thomas Lukasiewicz 외

For AI systems to garner widespread public acceptance, we must develop methods capable of explaining the decisions of black-box models such as neural networks. In this work, we identify two issues of current explanatory …

feature selection