The Loss Landscape Of Overparameterized Neural Networks
ASecurity
**arXiv ID:** 1804.10200 **Authors:** Y Cooper **Published:** 2018-04-26T17:58:45Z **Abstract:** We explore some mathematical features of the loss landscape of overparameterized neural networks. A priori one might imagine that the loss function looks like a typical function from $\mathbb{R}^n$ to $\mathbb{R}$ - in particular, nonconvex, with discrete global minima. In this paper, we prove that in at least one important way, the loss function of an overparameterized neural network does not loo...
Installs into .claude/skills of the current project.
Sponsors
SSkills DirectorySkills Directory
Know which skills are safe — weekly.
SSkills DirectorySkills Directory
Is that skill safe to install?
Are you the author of The Loss Landscape Of Overparameterized Neural Networks?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/hiyenwong-the-loss-landscape-of-overparameterized-neural-net)
# The loss landscape of overparameterized neural networks
**arXiv ID:** 1804.10200
**Authors:** Y Cooper
**Published:** 2018-04-26T17:58:45Z
**Abstract:**
We explore some mathematical features of the loss landscape of overparameterized neural networks. A priori one might imagine that the loss function looks like a typical function from $\mathbb{R}^n$ to $\mathbb{R}$ - in particular, nonconvex, with discrete global minima. In this paper, we prove that in at least one important way, the loss function of an overparameterized neural network does not look like a typical function. If a neural net has $n$ parameters and is trained on $d$ data points, with $n>d$, we show that the locus $M$ of global minima of $L$ is usually not discrete, but rather an $n-d$ dimensional submanifold of $\mathbb{R}^n$. In practice, neural nets commonly have orders of magnitude more parameters than data points, so this observation implies that $M$ is typically a very high-dimensional subset of $\mathbb{R}^n$.
## Skill Description
This skill is generated from the arXiv paper: The loss landscape of overparameterized neural networks (1804.10200).
## How to Use
[To be filled in by the user or by future automation]
## References
- [arXiv:1804.10200](http://arxiv.org/abs/1804.10200v1)
