| NEW: |
R. Kondor, Z. Lin and S. Trivedi:
Clebsch-Gordan Nets: a Fully Fourier Space Spherical Convolutional Neural Network
(NeurIPS 2018)
|
| NEW: |
T. Son Hy, S. Trivedi, H. Pan, B. M. Anderson and R. Kondor:
Predicting Molecular Properties with Covariant Compositional Networks
(JCP
special issue on data enabled theoretical chemistry, June 2018)
[pdf]
|
| NEW: |
R. Kondor:
N-body networks: a covariant hierarchical neural network architecture for learning
atomic potentials (preprint 3/5/18)
|
| NEW: |
R. Kondor and S. Trivedi:
On the generalization of equivariance and convolution in neural networks to the action of
compact groups (ICML 2018)
[poster]
[slides]
|
| Current Research |
Multiresolution/multiscale matrix factorizations
Machine learning for many-particle physics
Learning (on) graphs and other combinatorial structures
Permutation problems and Fourier analysis on the symmetric group
NEW:
Generalized covariant neural network architectures
|
| Postdoc |
Brandon Anderson
|
| Students |
Yi Ding (CS PhD, 4th year)
Jonathan Eskreis-Winkler (Stats PhD, 5th year)
Hy Truong Son (CS PhD, 3rd year)
Pramod K Mudrakarta (CS PhD, 5th year)
Horace Pan (CS PhD, 4th year)
|
| Other student collaborators |
Vikas Garg (MIT)
Shubhendu Trivedi (TTI-C)
|
Graduated
students
|
Nedelina Teneva (Amazon)
Maia Fraser
(assistant prof. at the University of Ottawa)
|
| Courses |
Winter 2019: CMSC 25400/STAT 27725 Machine Learning (undergraduate)
Spring 2019: STAT 37710/CMSC 35400 Machine Learning (graduate)
Spring 2019: CMSC 35401-1 Topics:
High performance ML system design
|
-->
| Recent papers |
R. Kondor, Z. Lin and S. Trivedi:
Clebsch-Gordan Nets: a Fully Fourier Space Spherical Convolutional Neural Network (preprint 6/24/18)
T. Son Hy, S. Trivedi, H. Pan, B. M. Anderson and R. Kondor:
Predicting Molecular Properties with Covariant Compositional Networks
(JCP
special issue on data enabled theoretical chemistry, June 2018)
[pdf]
R. Kondor:
N-body networks: a covariant hierarchical neural network architecture for learning
atomic potentials (preprint 3/5/18)
R. Kondor and S. Trivedi:
On the generalization of equivariance and convolution in neural networks to the action of
compact groups (ICML 2018)
R. Kondor, Hy Truong Son, Horace Pan, Brandon Anderson, Shubhendu Trivedi:
Covariant compositional networks for learning graphs (preprint)
[PyTorch code]
[GraphFlow]
[video]
Y. Ding, R. Kondor and J. Eskreis-Winkler:
Multiresolution kernel approximation for Gaussian process regression (NIPS 2017)
P. K. Mudrakarta and R. Kondor:
A generic multiresolution preconditioner for sparse symmetric systems (preprint)
K. Rajendran, A. A. Kattis, A. Holiday, R. Kondor and I. G. Kevrekidis:
Data mining when each data point is a network
(to appear in "Patterns of Dynamics", Springer Proceedings)
V. Ithapu, R. Kondor and V. Singh:
The Incremental Multiresolution Matrix Factorization Algorithm
(CVPR 2017)
R. Kondor and H. Pan:
The Multiscale Laplacian Graph Kernel
(NIPS 2016 oral presentation)
[arXiv]
[code]
[slides]
N. Teneva, P. K. Mudrakarta and R. Kondor:
Multiresolution Matrix Compression
(AISTATS 2016, winner of notable student paper award)
R. Kondor, N. Teneva and P. K. Mudrakarta:
Parallel MMF: a Multiresolution Approach to Matrix Computation
(arXiv preprint, July 2015)
[pMMF library]
G. Plumb, D. Pachauri, R. Kondor and V. Singh:
SnFFT: a Julia Toolkit for Harmonic Analysis on the Symmetric Group (JMLR 2015)
D. Pachauri, R. Kondor, G. Sargur and V. Singh:
Permutation diffusion maps with application to the image association problem in computer vision
(NIPS 2014)
R. Kondor, N. Teneva and V. Garg:
Multiresolution Matrix Factorization (ICML 2014)
[supplement]
[video]
|
| Recent events |
Multiresolution Methods for Large Scale Learning workshop at
NIPS 2015
[videos]
IMA Summer School on Modern Applications of Representation Theory
Chicago, July 21 - August 6, 2014
(co-organized with Jason Morton and Lek-Heng Lim)
[videos]
|
| Software |
SnOB:
a C++ library for computing fast Fourier transforms on the symmetric group
pMMF:
a high performance C++ library for parallel Multiresolution Matrix Factorization
Mondrian: C++ parallel blocked matrix library
GraphFlow:
a C++ deep learning library with support for covariant compositional architectures
(Hy Truong Son)
|
| Links |
All papers by topic
Curriculum Vitae
Detached threads blog
|
|
