paper-with-me

홈 › Papers

Quantitative convergence of trained single layer neural networks to Gaussian processes

2025-09-29 · Eloy Mosig, Andrea Agazzi, Dario Trevisan arxiv

In this paper, we study the quantitative convergence of shallow neural networks trained via gradient descent to their associated Gaussian processes in the infinite-width limit. While previous work has established qualitative convergence under broad settings, precise, finite-width estimates remain limited, particularly during training. We provide explicit upper bounds on the quadratic Wasserstein distance between the network output and its Gaussian approximation at any training time $t \ge 0$, demonstrating polynomial decay with network width. Our results quantify how architectural parameters, such as width and input dimension, influence convergence, and how training dynamics affect the approximation error.

📄 PDF Abstract BibTeX arXiv:2509.24544

Code (0)

등록된 구현이 없습니다.

Tasks

Gaussian Processes

Similar Papers 제목 키워드 기반

Quantitative Gaussian Approximation of Randomly Initialized Deep Neural Networks

2022-03-14 · Andrea Basteri, Dario Trevisan

Given any deep fully connected neural network, initialized with random Gaussian parameters, we bound from above the quadratic Wasserstein distance between its output distribution and a suitable Gaussian process. Our expl…

Entropic bounds for conditionally Gaussian vectors and applications to neural networks

2025-04-11 · Lucia Celli, Giovanni Peccati

Using entropic inequalities from information theory, we provide new bounds on the total variation and 2-Wasserstein distances between a conditionally Gaussian law and a Gaussian law with invertible covariance matrix. We …

The Gaussian equivalence of generative models for learning with shallow neural networks

2020-06-25 · Sebastian Goldt, Bruno Loureiro, Galen Reeves, Florent Krzakala 외

Understanding the impact of data structure on the computational tractability of learning is a key challenge for the theory of neural networks. Many theoretical works do not explicitly model training data, or assume that …

BIG-bench Machine Learning

On the Training Convergence of Transformers for In-Context Classification of Gaussian Mixtures

2024-10-15 · Wei Shen, Ruida Zhou, Jing Yang, Cong Shen

Although transformers have demonstrated impressive capabilities for in-context learning (ICL) in practice, theoretical understanding of the underlying mechanism that allows transformers to perform ICL is still in its inf…

In-Context Learning

Convergence Analysis of Two-Layer Neural Networks under Gaussian Input Masking

2026-02-19 · Afroditi Kolomvaki, Fangshuo Liao, Evan Dramko, Ziyun Guang 외 arxiv

We investigate the convergence guarantee of two-layer neural network training with Gaussian randomly masked inputs. This scenario corresponds to Gaussian dropout at the input level, or noisy input training common in sens…

Federated Learning