Research map / Learning theory and algorithms / Prediction and decision losses
The Role of Over-Parameterization in Machine Learning – the Good, the Bad, the Ugly
Fanghui Liu
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
An AAAI 2024 talk abstract discussing theoretical understanding of the role of over-parameterization in neural networks.
Problem
Understanding why over-parameterized neural networks, with far more parameters than training examples, work well from a theoretical standpoint.
Approach
Based only on the abstract, the talk aims to theoretically explain the role of over-parameterization in neural networks, framing it as good, bad, and ugly aspects.
Closest papers by meaning
- On Learning Over-parameterized Neural Networks: A Functional Approximation Perspective (NeurIPS 2019 · similarity 0.88)
- Improving Adaptivity via Over-Parameterization in Sequence Models (NeurIPS 2024 · similarity 0.87)
- Exploring the Complexity of Deep Neural Networks through Functional Equivalence (ICML 2024 · similarity 0.85)
- Bias of Stochastic Gradient Descent or the Architecture: Disentangling the Effects of Overparameterization of Neural Networks (ICML 2024 · similarity 0.85)
- Simplicity Bias in Overparameterized Machine Learning (AAAI 2024 · similarity 0.85)
- Tilting the Odds at the Lottery: the Interplay of Overparameterisation and Curricula in Neural Networks (ICML 2024 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
