activity
20162022
most citedSymmetries, flat minima, and the conserved quantities of gradient flow

2 citations · 3 across the 3 of their papers we have counts for

collaborators

7 papers

cs.LG2022★ 2 cited

Symmetries, flat minima, and the conserved quantities of gradient flow

Bo Zhao, Iordan Ganev, Robin Walters +2

Empirical studies of the loss landscape of deep networks have revealed that many local minima are connected through low-loss valleys. Yet, little is known about the theoretical ori…

cs.LG2022

Quiver neural networks

Iordan Ganev, Robin Walters

We develop a uniform theoretical approach towards the analysis of various neural network connectivity architectures by introducing the notion of a quiver neural network. Inspired b…

cs.LG2021★ 1 cited

Universal approximation and model compression for radial neural networks

Iordan Ganev, Twan van Laarhoven, Robin Walters

We introduce a class of fully-connected neural networks whose activation functions, rather than being pointwise, rescale feature vectors by a function depending only on their norm.…

math.QA2019

Quantum Weyl algebras and reflection equation algebras at a root of unity

Nicholas Cooney, Iordan Ganev, David Jordan

We compute the center and Azumaya locus in the simplest non-abelian examples of quantized multiplicative quiver varieties at a root of unity: quantum Weyl algebras of rank , and…

math.QA2019

The quantum Frobenius for character varieties and multiplicative quiver varieties

Iordan Ganev, David Jordan, Pavel Safronov

We prove that quantized multiplicative quiver varieties and quantum character varieties define sheaves of Azumaya algebras over the corresponding classical moduli spaces, and we pr…

math.RT2019

Wonderful asymptotics of matrix coefficient D-modules

David Ben-Zvi, Iordan Ganev

Beilinson-Bernstein localization realizes representations of complex reductive Lie algebras as monodromic -modules on the "basic affine space" , a torus bundle over the fla…