Alert button
Picture for Marc Finzi

Marc Finzi

Alert button

Non-Vacuous Generalization Bounds for Large Language Models

Dec 28, 2023
Sanae Lotfi, Marc Finzi, Yilun Kuang, Tim G. J. Rudner, Micah Goldblum, Andrew Gordon Wilson

Viaarxiv icon

Large Language Models Are Zero-Shot Time Series Forecasters

Oct 11, 2023
Nate Gruver, Marc Finzi, Shikai Qiu, Andrew Gordon Wilson

Viaarxiv icon

CoLA: Exploiting Compositional Structure for Automatic and Efficient Numerical Linear Algebra

Sep 06, 2023
Andres Potapczynski, Marc Finzi, Geoff Pleiss, Andrew Gordon Wilson

Figure 1 for CoLA: Exploiting Compositional Structure for Automatic and Efficient Numerical Linear Algebra
Figure 2 for CoLA: Exploiting Compositional Structure for Automatic and Efficient Numerical Linear Algebra
Figure 3 for CoLA: Exploiting Compositional Structure for Automatic and Efficient Numerical Linear Algebra
Figure 4 for CoLA: Exploiting Compositional Structure for Automatic and Efficient Numerical Linear Algebra
Viaarxiv icon

User-defined Event Sampling and Uncertainty Quantification in Diffusion Models for Physical Dynamical Systems

Jun 13, 2023
Marc Finzi, Anudhyan Boral, Andrew Gordon Wilson, Fei Sha, Leonardo Zepeda-Núñez

Figure 1 for User-defined Event Sampling and Uncertainty Quantification in Diffusion Models for Physical Dynamical Systems
Figure 2 for User-defined Event Sampling and Uncertainty Quantification in Diffusion Models for Physical Dynamical Systems
Figure 3 for User-defined Event Sampling and Uncertainty Quantification in Diffusion Models for Physical Dynamical Systems
Figure 4 for User-defined Event Sampling and Uncertainty Quantification in Diffusion Models for Physical Dynamical Systems
Viaarxiv icon

A Stable and Scalable Method for Solving Initial Value PDEs with Neural Networks

Apr 28, 2023
Marc Finzi, Andres Potapczynski, Matthew Choptuik, Andrew Gordon Wilson

Figure 1 for A Stable and Scalable Method for Solving Initial Value PDEs with Neural Networks
Figure 2 for A Stable and Scalable Method for Solving Initial Value PDEs with Neural Networks
Figure 3 for A Stable and Scalable Method for Solving Initial Value PDEs with Neural Networks
Figure 4 for A Stable and Scalable Method for Solving Initial Value PDEs with Neural Networks
Viaarxiv icon

The No Free Lunch Theorem, Kolmogorov Complexity, and the Role of Inductive Biases in Machine Learning

Apr 11, 2023
Micah Goldblum, Marc Finzi, Keefer Rowan, Andrew Gordon Wilson

Figure 1 for The No Free Lunch Theorem, Kolmogorov Complexity, and the Role of Inductive Biases in Machine Learning
Figure 2 for The No Free Lunch Theorem, Kolmogorov Complexity, and the Role of Inductive Biases in Machine Learning
Figure 3 for The No Free Lunch Theorem, Kolmogorov Complexity, and the Role of Inductive Biases in Machine Learning
Figure 4 for The No Free Lunch Theorem, Kolmogorov Complexity, and the Role of Inductive Biases in Machine Learning
Viaarxiv icon

PAC-Bayes Compression Bounds So Tight That They Can Explain Generalization

Nov 24, 2022
Sanae Lotfi, Marc Finzi, Sanyam Kapoor, Andres Potapczynski, Micah Goldblum, Andrew Gordon Wilson

Figure 1 for PAC-Bayes Compression Bounds So Tight That They Can Explain Generalization
Figure 2 for PAC-Bayes Compression Bounds So Tight That They Can Explain Generalization
Figure 3 for PAC-Bayes Compression Bounds So Tight That They Can Explain Generalization
Figure 4 for PAC-Bayes Compression Bounds So Tight That They Can Explain Generalization
Viaarxiv icon

The Lie Derivative for Measuring Learned Equivariance

Oct 06, 2022
Nate Gruver, Marc Finzi, Micah Goldblum, Andrew Gordon Wilson

Figure 1 for The Lie Derivative for Measuring Learned Equivariance
Figure 2 for The Lie Derivative for Measuring Learned Equivariance
Figure 3 for The Lie Derivative for Measuring Learned Equivariance
Figure 4 for The Lie Derivative for Measuring Learned Equivariance
Viaarxiv icon

Deconstructing the Inductive Biases of Hamiltonian Neural Networks

Feb 12, 2022
Nate Gruver, Marc Finzi, Samuel Stanton, Andrew Gordon Wilson

Figure 1 for Deconstructing the Inductive Biases of Hamiltonian Neural Networks
Figure 2 for Deconstructing the Inductive Biases of Hamiltonian Neural Networks
Figure 3 for Deconstructing the Inductive Biases of Hamiltonian Neural Networks
Figure 4 for Deconstructing the Inductive Biases of Hamiltonian Neural Networks
Viaarxiv icon

Residual Pathway Priors for Soft Equivariance Constraints

Dec 02, 2021
Marc Finzi, Gregory Benton, Andrew Gordon Wilson

Figure 1 for Residual Pathway Priors for Soft Equivariance Constraints
Figure 2 for Residual Pathway Priors for Soft Equivariance Constraints
Figure 3 for Residual Pathway Priors for Soft Equivariance Constraints
Figure 4 for Residual Pathway Priors for Soft Equivariance Constraints
Viaarxiv icon