2021
DOI: 10.48550/arxiv.2108.01538
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

Geometry of Linear Convolutional Networks

Abstract: We study the family of functions that are represented by a linear convolutional neural network (LCN). These functions form a semi-algebraic subset of the set of linear maps from input space to output space. In contrast, the families of functions represented by fully-connected linear networks form algebraic sets. We observe that the functions represented by LCNs can be identified with polynomials that admit certain factorizations, and we use this perspective to describe the impact of the network's architecture … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1

Citation Types

0
2
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
1
1

Relationship

0
2

Authors

Journals

citations
Cited by 2 publications
(2 citation statements)
references
References 15 publications
0
2
0
Order By: Relevance
“…We already mentioned above the Burer-Monteiro approach to semidefinite programming [9,14], low-rank optimization [22,32,36], computer vision [17], and neural networks [38]. In [47,29], the authors compare the stationary points for (Q) to those of (P) for the case of linear neural networks and prove a special case of our Theorem 2.10 characterizing "1 ⇒ 1". The training of general neural networks, and risk minimization more generally, is naturally given in the form (Q), see [47,Appx.…”
Section: Prior Workmentioning
confidence: 99%
“…We already mentioned above the Burer-Monteiro approach to semidefinite programming [9,14], low-rank optimization [22,32,36], computer vision [17], and neural networks [38]. In [47,29], the authors compare the stationary points for (Q) to those of (P) for the case of linear neural networks and prove a special case of our Theorem 2.10 characterizing "1 ⇒ 1". The training of general neural networks, and risk minimization more generally, is naturally given in the form (Q), see [47,Appx.…”
Section: Prior Workmentioning
confidence: 99%
“…Similarly to the tensor case, this implies that proofs of guarantees for training algorithms must exploit the structure in specific cost functions (the loss). Additional study of lifts defined by linear neural networks was done in [32,54], where the authors characterize (in our terminology) "1 ⇒1" for lifts defined by linear and linear convolutional architectures.…”
Section: Neural Networkmentioning
confidence: 99%