Marc Finzi
Marc Finzi
Postdoc at Carnegie Mellon University
Verified email at - Homepage
Cited by
Cited by
Generalizing convolutional neural networks for equivariance to lie groups on arbitrary continuous data
M Finzi, S Stanton, P Izmailov, AG Wilson
International Conference on Machine Learning (ICML), 2020
There are many consistent explanations of unlabeled data: Why you should average
B Athiwaratkun, M Finzi, P Izmailov, AG Wilson
International Conference on Learning Representations (ICLR), 2018
A practical method for constructing equivariant multilayer perceptrons for arbitrary matrix groups
M Finzi, M Welling, AG Wilson
ICML 2021, 2021
Learning invariances in neural networks from training data
G Benton, M Finzi, P Izmailov, AG Wilson
Advances in neural information processing systems 33, 17605-17616, 2020
Simplifying hamiltonian and lagrangian neural networks via explicit constraints
M Finzi, KA Wang, AG Wilson
Advances in neural information processing systems 33, 13880-13889, 2020
Semi-supervised learning with normalizing flows
P Izmailov, P Kirichenko, M Finzi, AG Wilson
ICML 2020, 2020
Large language models are zero-shot time series forecasters
N Gruver, M Finzi, S Qiu, AG Wilson
NeurIPS 2023, 2024
Deconstructing the inductive biases of hamiltonian neural networks
N Gruver, M Finzi, S Stanton, AG Wilson
ICLR 2022, 2022
Residual pathway priors for soft equivariance constraints
M Finzi, G Benton, AG Wilson
NeurIPS 2021, 2021
PAC-bayes compression bounds so tight that they can explain generalization
S Lotfi, M Finzi, S Kapoor, A Potapczynski, M Goldblum, AG Wilson
NeurIPS 2022, 2022
Improving consistency-based semi-supervised learning with weight averaging
B Athiwaratkun, M Finzi, P Izmailov, AG Wilson
arXiv preprint arXiv:1806.05594 2 (9), 11, 2018
The lie derivative for measuring learned equivariance
N Gruver, M Finzi, M Goldblum, AG Wilson
ICML 2023, 2022
Invertible convolutional networks
M Finzi, P Izmailov, W Maddox, P Kirichenko, AG Wilson
Workshop on Invertible Neural Nets and Normalizing Flows, International…, 2019
Probabilistic numeric convolutional neural networks
M Finzi, R Bondesan, M Welling
arXiv preprint arXiv:2010.10876, 2020
Effective surrogate models for protein design with bayesian optimization
N Gruver, S Stanton, P Kirichenko, M Finzi, P Maffettone, V Myers, ...
ICML Workshop on Computational Biology 183, 2021
Skiing on simplices: Kernel interpolation on the permutohedral lattice for scalable gaussian processes
S Kapoor, M Finzi, KA Wang, AGG Wilson
ICML 2021, 2021
The no free lunch theorem, kolmogorov complexity, and the role of inductive biases in machine learning
M Goldblum, M Finzi, K Rowan, AG Wilson
arXiv preprint arXiv:2304.05366, 2023
A Stable and Scalable Method for Solving Initial Value PDEs with Neural Networks
M Finzi, A Potapczynski, M Choptuik, AG Wilson
ICLR 2023, 2023
User-defined event sampling and uncertainty quantification in diffusion models for physical dynamical systems
MA Finzi, A Boral, AG Wilson, F Sha, L Zepeda-Nez
ICML 2023, 2023
Non-vacuous generalization bounds for large language models
S Lotfi, M Finzi, Y Kuang, TGJ Rudner, M Goldblum, AG Wilson
arXiv preprint arXiv:2312.17173, 2023
The system can't perform the operation now. Try again later.
Articles 1–20