This event is part of Algebraic Statistics and Our Changing World View Details

Bayesian Statistics and Statistical Learning

New Directions in Algebraic Statistics

Description

Back to top

This workshop will explore new directions for algebraic statistics in the realm of Bayesian statistics and statistical learning.  The considered topics will cover a broad range of problems from modern statistics and machine learning for which underlying algebraic structure provides a common theme.  Topics of particular interest are singular models and variational inference, invariance and equivariance in statistics and machine learning, and new interdisciplinary connections between computational algebraic geometry and machine learning.  

Organizers

Back to top
M D
Mathias Drton Technical University of Munich
​ H
​Jonathan Hauenstein University of Notre Dame
L L
Lek-Heng Lim University of Chicago
D P
Debdeep Pati Texas A&M University

Speakers

Back to top
B A
Bryon Aragam University of Chicago
E C
Emma Cobian University of Notre Dame
J d L
Jesús de Loera University of California, Davis (UC Davis)
N D
Nadav Dym Technion – Israel Institute of Technology
K H
Kathryn Heal Google
P H
Peter Hoff Duke University
V K
Vishesh Karwa Temple University
J K
Joe Kileel University of Texas, Austin
K K
Kathlén Kohn KTH Royal Institute of Technology
R K
Risi Kondor University of Chicago
S L
Shaowei Lin Topos Institute
A M
Andrew McCormack Duke University
G M
Guido Montufar University of California, Los Angeles (UCLA)
L N
Long Nguyen University of Michigan
L O
Luke Oeding Auburn University
S P
Sean Plummer University of Arkansas
J R
Judith Rousseau University of Oxford
K W
Kazuho Watanabe Toyohashi University of Technology
S W
Sumio Watanabe Tokyo Institute of Technology
H X
Han Xiao Rutgers University

Schedule

Back to top
Monday, December 11, 2023
9:30-10:30 CST
Online learning for spiking neural networks with relative information rate

Speaker: Shaowei Lin (Topos Institute)

10:30-11:00 CST
Coffee Break
11:00-12:00 CST
Rate-Distortion Theoretical Views of Bayesian Learning Coefficients

Speaker: Kazuho Watanabe (Toyohashi University of Technology)

12:00-13:00 CST
Nonstandard minimax rates in nonparametric latent variable models and representation learning

Speaker: Bryon Aragam (University of Chicago)

13:00-14:00 CST
Lunch
14:00-15:00 CST
Mathematical aspects of equivariant neural networks

Speaker: Risi Kondor (University of Chicago)

15:00-16:00 CST
Coffee Break
16:00-16:30 CST
Bias and Variance of Bayes Cross Validation in Singular Learning Theory

Speaker: Sumio Watanabe (Tokyo Institute of Technology)

Tuesday, December 12, 2023
9:00-10:00 CST
Differential privacy for networks and tables 

Speaker: Vishesh Karwa (Temple University)

10:00-10:30 CST
Coffee Break
10:30-11:30 CST
Equivariant Estimation of Fréchet Means

Speaker: Andrew McCormack (Duke University)

11:30-12:30 CST
Minimum distance estimators and inverse bounds for latent probability measures

Speaker: Xuanlong Nguyen (University of Michigan)

12:30-13:30 CST
Lunch
13:30-14:30 CST
Equivariant Variance Estimation for Multiple Change-point Model

Speaker: Han Xiao (Rutgers University)

14:30-15:00 CST
Coffee Break
15:00-16:00 CST
TBD

Speaker: Judith Rousseau (University of Oxford)

Wednesday, December 13, 2023
9:00-10:00 CST
Geometry of Linear Neural Networks that are Equivariant /  Invariant under Permutation Groups

Speaker: Kathlén Kohn (KTH Royal Institute of Technology)

10:00-10:30 CST
Coffee Break
10:30-11:30 CST
Core Shrinkage Covariance Estimation for Matrix-variate Data

Speaker: Peter Hoff (Duke University)

11:30-12:30 CST
Characterizing the spectrum of the neural tangent kernel via a power series expansion

Speaker: Guido Montufar (UCLA)

12:30-14:00 CST
Social Hour & Lunch
14:00-15:00 CST
Efficient Invariant Embeddings for multisets, point sets, and graphs

Speaker: Nadav Dym (Technion – Israel Institute of Technology)

15:00-16:00 CST
Group Work
Thursday, December 14, 2023
9:00-10:00 CST
Highlights from the Long Program
10:00-10:30 CST
Coffee Break
10:30-11:30 CST
Variational Inference in Singular Models

Speaker: Sean Plummer (University of Arkansas)

11:30-12:30 CST
Markov Bases: A 25-year update

Speaker: Jesús De Loera (University of California, Davis (UC Davis))

12:30-13:30 CST
Lunch
13:30-14:30 CST
Learning Entanglement Types

Speaker: Luke Oeding (Auburn University)

14:30-15:00 CST
Coffee Break
15:00-16:00 CST
Open Discussion
Friday, December 15, 2023
9:30-10:00 CST
Navigating Gauss-Manin Connections Using Deep Learning

Speaker: Kathryn Heal (Google)

10:00-10:30 CST
Coffee Break
10:30-11:30 CST
Homotopy Continuation Techniques for Optimization in Variational Inference

Speaker: Emma Cobian (University of Notre Dame)

11:30-12:30 CST
Covering Number of Real Algebraic Varieties and Beyond: Improved Bounds and Applications

Speaker: Joe Kileel (University of Texas at Austin)

12:30-13:30 CST
Lunch
13:30-14:30 CST
Closing Discussion
14:30-15:00 CST
Coffee & End

Videos

Back to top

Online learning for spiking neural networks with relative information rate

Shaowei Lin
December 11, 2023

Rate-Distortion Theoretical Views of Bayesian Learning Coefficients

Kazuho Watanabe
December 11, 2023

Nonstandard minimax rates in nonparametric latent variable models and representation learning

Bryon Aragam
December 11, 2023

Mathematical aspects of equivariant neural networks

Risi Kondor
December 11, 2023

Bias and Variance of Bayes Cross Validation in Singular Learning Theory

Sumio Watanabe
December 11, 2023

Differential privacy for networks and tables 

Vishesh Karwa
December 12, 2023

Equivariant Estimation of Fréchet Means

Andrew McCormack
December 12, 2023

Minimum distance estimators and inverse bounds for latent probability measures

Xuanlong Nguyen
December 12, 2023

Equivariant Variance Estimation for Multiple Change-point Model

Han Xiao
December 12, 2023

On multivariate deconvolution with Wasserstein loss: minimax rates and Bayesian contraction rates

Judith Rousseau
December 12, 2023

Geometry of Linear Neural Networks that are Equivariant /  Invariant under Permutation Groups

Kathlén Kohn
December 13, 2023

Core Shrinkage Covariance Estimation for Matrix-variate Data

Peter Hoff
December 13, 2023

Characterizing the spectrum of the neural tangent kernel via a power series expansion

Guido Montufar
December 13, 2023

Efficient Invariant Embeddings for multisets, point sets, and graphs

Nadav Dym
December 13, 2023

Highlights from the Long Program


December 14, 2023

Variational Inference in Singular Models

Sean Plummer
December 14, 2023

Markov Bases: A 25-year update

Jesús De Loera
December 14, 2023

Learning Entanglement Types

Luke Oeding
December 14, 2023

Homotopy Continuation Techniques for Optimization in Variational Inference

Emma Cobian
December 15, 2023

Covering Number of Real Algebraic Varieties and Beyond: Improved Bounds and Applications

Joe Kileel
December 15, 2023