paper-with-me

홈 › Papers

Plateaus, Optima, and Overfitting in Multi-Layer Perceptrons: A Saddle-Saddle-Attractor Scenario

2026-04-02 · Alex Alì Maleknia, Yuzuru Sato arxiv

Vanishing gradients and overfitting are central problems in machine learning, yet are typically analyzed in asymptotic regimes that obscure their dynamical origins. Here we provide a dynamical description of learning in multi-layer perceptrons (MLPs) via a minimal model inspired by Fukumizu and Amari. We show that training dynamics traverse plateau and near-optimal regions, both organized by saddle structures, before converging to an overfitting regime. Under suitable conditions on the data, this regime collapses to a single attractor modulo symmetry. Furthermore, for finite noisy datasets, convergence to the theoretical optimum is impossible, and the dynamics necessarily settle into an overfitting solution.

📄 PDF Abstract BibTeX arXiv:2604.02393

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Graph Contrastive Learning versus Untrained Baselines: The Role of Dataset Size

2025-09-01 · Smayan Khanna, Doruk Efe Gökmen, Risi Kondor, Vincenzo Vitelli arxiv

Graph Contrastive Learning (GCL) has emerged as a leading paradigm for self-supervised learning on graphs, with strong performance reported on standardized datasets and growing applications ranging from genomics to drug …

Self-Supervised LearningContrastive LearningDrug Discovery

SyntNN at SemEval-2018 Task 2: is Syntax Useful for Emoji Prediction? Embedding Syntactic Trees in Multi Layer Perceptrons

2018-06-01 · SEMEVAL 2018 6 · Fabio Massimo Zanzotto, Andrea Santilli

In this paper, we present SyntNN as a way to include traditional syntactic models in multilayer neural networks used in the task of Semeval Task 2 of emoji prediction. The model builds on the distributed tree embedder al…

Task 2

RandomForestMLP: An Ensemble-Based Multi-Layer Perceptron Against Curse of Dimensionality

2020-11-02 · Mohamed Mejri, Aymen Mejri

We present a novel and practical deep learning pipeline termed RandomForestMLP. This core trainable classification engine consists of a convolutional neural network backbone followed by an ensemble-based multi-layer perc…

ClassificationGeneral Classification

Avoiding overfitting of multilayer perceptrons by training derivatives

2018-02-28 · V. I. Avrutskiy

Resistance to overfitting is observed for neural networks trained with extended backpropagation algorithm. In addition to target values, its cost function uses derivatives of those up to the $4^{\mathrm{th}}$ order. For …

Dropout Regularization in Hierarchical Mixture of Experts

2018-12-25 · Ozan İrsoy, Ethem Alpaydin

Dropout is a very effective method in preventing overfitting and has become the go-to regularizer for multi-layer neural networks in recent years. Hierarchical mixture of experts is a hierarchically gated model that defi…

Mixture-of-Experts