Search

Login
MiS Profile

Guido Montúfar

Portrait of Guido Montúfar
Research Group Leader

Guido Montúfar

Research Group Leader
Email - 731 E2 05
Mathematical Machine Learning MiS Profile MiS Profile
/

Research

My research interests are:

  • Deep Learning Theory
  • Mathematical Machine Learning
  • Graphical Models
  • Information Geometry
  • Algebraic Statistics

Assistant Professor, Departments of Mathematics and Statistics, UCLA (since 07/2017)

Research Group Leader, Mathematical Machine Learning Group, Max Planck Institute for Mathematics in the Sciences (since 07/2018)

Postdoc, Max Planck Institute for Mathematics in the Sciences, Information Theory of Cognitive Systems Group (06/2013-09/2017)

Research Associate, Department of Mathematics, Pennsylvania State University (02/2012-05/2013)

PhD in Mathematics, MPI MIS, Leipzig University (10/2012)

Research Assistant, Institute for Theoretical Physics, TU-Berlin (03/2008-12/2008)

Diplom Physiker, TU-Berlin (12/2008)

Teaching Assistant, Institute for Mathematics, TU-Berlin (03/2006-02/2008)

Diplom Mathematiker, TU-Berlin (08/2007)

Publications

inJournal
2024
Mareike Dressler et al.

Algebraic optimization of sequential decision problems

In: Journal of symbolic computation

BibTex

 DOI: 10.1016/j.jsc.2023.102241 ArXiv: 2211.09439
inJournal
2024
Johannes Müller et al.

Geometry and convergence of natural policy gradient methods

In: Information geometry

BibTex

 DOI: 10.1007/s41884-023-00106-z ArXiv: 2211.02105

MiS Preprint
inJournal
2023
Hui Jin et al.

Implicit bias of gradient descent for mean squared error regression with wide neural networks

In: Journal of machine learning research

BibTex

 ArXiv: 2006.07356

MiS Preprint
Preprint
2023
Kedar Karhadkar et al.

Mildly overparameterized ReLU networks have a favorable loss landscape

BibTex

 ArXiv: 2305.19510
Preprint
2023
Kathlén Kohn et al.

Function space and critical points of linear convolutional networks

(SIAM journal on discrete mathematics)

BibTex

 ArXiv: 2304.05752
inBook
2023
Thomas Merkh et al.

Stochastic feedforward neural networks : universal approximation

In: Mathematical aspects of deep learning

BibTex

 DOI: 10.1017/9781009025096.007 ArXiv: 1910.09763
inJournal
2023
Johannes Rauh et al.

Continuity and additivity properties of information decompositions

In: International journal of approximate reasoning

BibTex

 DOI: 10.1016/j.ijar.2023.108979 ArXiv: 2204.10982
Preprint
2023
Rishi Sonthalia et al.

Supermodular rank : set function decomposition and optimization

BibTex

 ArXiv: 2305.14632
Preprint
2023
Hanna Tseran et al.

Expected gradients of maxout networks and consequences to parameter initialization

BibTex

 ArXiv: 2301.06956 Link: openreview.net
inBook
2022
Pradeep Kumar Banerjee et al.

Oversquashing in GNNs through the lens of information contraction and graph expansion

In: 2022 58th Annual Allerton Conference on communication, control, and computing : 27-30 Sept. 2022

BibTex

 DOI: 10.1109/ALLERTON49937.2022.9929363 ArXiv: 2208.03471

MiS Preprint
Preprint
2022
Benjamin Bowman et al.

Implicit bias of MSE gradient optimization in underparameterized neural networks

BibTex

 ArXiv: 2201.04738
inBook
2022
Benjamin Bowman et al.

Spectral bias outside the training set for deep networks in the kernel regime

In: Advances in neural information processing systems 35 : NeurIPS 2022 ; annual conference on neural information processing systems 2022

BibTex

 ArXiv: 2206.02927 Link: proceedings.neurips.cc
All Personal Publications
/