[图书][B] Metric algebraic geometry

P Breiding, K Kohn, B Sturmfels - 2024 - library.oapen.org
Metric algebraic geometry combines concepts from algebraic geometry and differential
geometry. Building on classical foundations, it offers practical tools for the 21st century …

On the minimal algebraic complexity of the rank-one approximation problem for general inner products

K Kozhasov, A Muniz, Y Qi, L Sodomaco - arXiv preprint arXiv:2309.15105, 2023 - arxiv.org
We study the algebraic complexity of Euclidean distance minimization from a generic tensor
to a variety of rank-one tensors. The Euclidean Distance (ED) degree of the Segre-Veronese …

The geometry of the deep linear network

G Menon - arXiv preprint arXiv:2411.09004, 2024 - arxiv.org
This article provides an expository account of training dynamics in the Deep Linear Network
(DLN) from the perspective of the geometric theory of dynamical systems. Rigorous results …

Geometry of lightning self-attention: Identifiability and dimension

NW Henry, GL Marchetti, K Kohn - arXiv preprint arXiv:2408.17221, 2024 - arxiv.org
We consider function spaces defined by self-attention networks without normalization, and
theoretically analyze their geometry. Since these networks are polynomial, we rely on tools …

Geometry of linear neural networks: Equivariance and invariance under permutation groups

K Kohn, AL Sattelberger, V Shahverdi - arXiv preprint arXiv:2309.13736, 2023 - arxiv.org
The set of functions parameterized by a linear fully-connected neural network is a
determinantal variety. We investigate the subvariety of functions that are equivariant or …

[HTML][HTML] The geometry of the neuromanifold

K Kohn - Collections, 2024 - siam.org
Machine learning with neural networks works quite well for a variety of applications, even
though the underlying optimization problems are highly nonconvex. Yet despite researchers' …

On the Geometry and Optimization of Polynomial Convolutional Networks

V Shahverdi, GL Marchetti, K Kohn - arXiv preprint arXiv:2410.00722, 2024 - arxiv.org
We study convolutional neural networks with monomial activation functions. Specifically, we
prove that their parameterization map is regular and is an isomorphism almost everywhere …

Algebraic Complexity and Neurovariety of Linear Convolutional Networks

V Shahverdi - arXiv preprint arXiv:2401.16613, 2024 - arxiv.org
In this paper, we study linear convolutional networks with one-dimensional filters and
arbitrary strides. The neuromanifold of such a network is a semialgebraic set, represented by …

[PDF][PDF] A Complete Bibliography of Publications in the SIAM Journal on Applied Algebra and Geometry

NHF Beebe - 2024 - netlib.org
A Complete Bibliography of Publications in the SIAM Journal on Applied Algebra and
Geometry Page 1 A Complete Bibliography of Publications in the SIAM Journal on Applied …