Marc Finzi

Publication Activity (10 Years)

Years Active: 2018-2024
Publications (10 Years): 31

Top Topics

Diffusion Models

Top Venues

Publications

Sanae Lotfi, Yilun Kuang, Brandon Amos, Micah Goldblum, Marc Finzi, Andrew Gordon Wilson
Unlocking Tokens as Data Points for Generalization Bounds on Larger Language Models. CoRR (2024)
Shikai Qiu, Andres Potapczynski, Marc Finzi, Micah Goldblum, Andrew Gordon Wilson
Compute Better Spent: Replacing Dense Layers with Structured Matrices. CoRR (2024)
Andres Potapczynski, Marc Finzi, Geoff Pleiss, Andrew Gordon Wilson
CoLA: Exploiting Compositional Structure for Automatic and Efficient Numerical Linear Algebra. NeurIPS (2023)
Micah Goldblum, Marc Finzi, Keefer Rowan, Andrew Gordon Wilson
The No Free Lunch Theorem, Kolmogorov Complexity, and the Role of Inductive Biases in Machine Learning. CoRR (2023)
Andres Potapczynski, Marc Finzi, Geoff Pleiss, Andrew Gordon Wilson
CoLA: Exploiting Compositional Structure for Automatic and Efficient Numerical Linear Algebra. CoRR (2023)
Sanae Lotfi, Marc Finzi, Yilun Kuang, Tim G. J. Rudner, Micah Goldblum, Andrew Gordon Wilson
Non-Vacuous Generalization Bounds for Large Language Models. CoRR (2023)
Nate Gruver, Marc Finzi, Shikai Qiu, Andrew Gordon Wilson
Large Language Models Are Zero-Shot Time Series Forecasters. NeurIPS (2023)
Marc Finzi, Anudhyan Boral, Andrew Gordon Wilson, Fei Sha, Leonardo Zepeda-Núñez
User-defined Event Sampling and Uncertainty Quantification in Diffusion Models for Physical Dynamical Systems. CoRR (2023)
Marc Finzi, Andres Potapczynski, Matthew Choptuik, Andrew Gordon Wilson
A Stable and Scalable Method for Solving Initial Value PDEs with Neural Networks. CoRR (2023)
Nate Gruver, Marc Finzi, Shikai Qiu, Andrew Gordon Wilson
Large Language Models Are Zero-Shot Time Series Forecasters. CoRR (2023)
Sanae Lotfi, Marc Finzi, Sanyam Kapoor, Andres Potapczynski, Micah Goldblum, Andrew Gordon Wilson
PAC-Bayes Compression Bounds So Tight That They Can Explain Generalization. NeurIPS (2022)
Nate Gruver, Marc Finzi, Micah Goldblum, Andrew Gordon Wilson
The Lie Derivative for Measuring Learned Equivariance. CoRR (2022)
Sanae Lotfi, Marc Finzi, Sanyam Kapoor, Andres Potapczynski, Micah Goldblum, Andrew Gordon Wilson
PAC-Bayes Compression Bounds So Tight That They Can Explain Generalization. CoRR (2022)
Nate Gruver, Marc Finzi, Samuel Stanton, Andrew Gordon Wilson
Deconstructing the Inductive Biases of Hamiltonian Neural Networks. CoRR (2022)
Sanyam Kapoor, Marc Finzi, Ke Alexander Wang, Andrew Gordon Wilson
SKIing on Simplices: Kernel Interpolation on the Permutohedral Lattice for Scalable Gaussian Processes. ICML (2021)
Marc Finzi, Max Welling, Andrew Gordon Wilson
A Practical Method for Constructing Equivariant Multilayer Perceptrons for Arbitrary Matrix Groups. CoRR (2021)
Marc Finzi, Gregory W. Benton, Andrew Gordon Wilson
Residual Pathway Priors for Soft Equivariance Constraints. CoRR (2021)
Marc Finzi, Greg Benton, Andrew Gordon Wilson
Residual Pathway Priors for Soft Equivariance Constraints. NeurIPS (2021)
Sanyam Kapoor, Marc Finzi, Ke Alexander Wang, Andrew Gordon Wilson
SKIing on Simplices: Kernel Interpolation on the Permutohedral Lattice for Scalable Gaussian Processes. CoRR (2021)
Marc Finzi, Max Welling, Andrew Gordon Wilson
A Practical Method for Constructing Equivariant Multilayer Perceptrons for Arbitrary Matrix Groups. ICML (2021)
Gregory W. Benton, Marc Finzi, Pavel Izmailov, Andrew Gordon Wilson
Learning Invariances in Neural Networks from Training Data. NeurIPS (2020)
Pavel Izmailov, Polina Kirichenko, Marc Finzi, Andrew Gordon Wilson
Semi-Supervised Learning with Normalizing Flows. ICML (2020)
Marc Finzi, Samuel Stanton, Pavel Izmailov, Andrew Gordon Wilson
Generalizing Convolutional Neural Networks for Equivariance to Lie Groups on Arbitrary Continuous Data. ICML (2020)
Marc Finzi, Roberto Bondesan, Max Welling
Probabilistic Numeric Convolutional Neural Networks. CoRR (2020)
Marc Finzi, Samuel Stanton, Pavel Izmailov, Andrew Gordon Wilson
Generalizing Convolutional Neural Networks for Equivariance to Lie Groups on Arbitrary Continuous Data. CoRR (2020)
Gregory W. Benton, Marc Finzi, Pavel Izmailov, Andrew Gordon Wilson
Learning Invariances in Neural Networks. CoRR (2020)
Marc Finzi, Ke Alexander Wang, Andrew Gordon Wilson
Simplifying Hamiltonian and Lagrangian Neural Networks via Explicit Constraints. NeurIPS (2020)
Marc Finzi, Ke Alexander Wang, Andrew Gordon Wilson
Simplifying Hamiltonian and Lagrangian Neural Networks via Explicit Constraints. CoRR (2020)
Pavel Izmailov, Polina Kirichenko, Marc Finzi, Andrew Gordon Wilson
Semi-Supervised Learning with Normalizing Flows. CoRR (2019)
Ben Athiwaratkun, Marc Finzi, Pavel Izmailov, Andrew Gordon Wilson
There Are Many Consistent Explanations of Unlabeled Data: Why You Should Average. ICLR (Poster) (2019)
Ben Athiwaratkun, Marc Finzi, Pavel Izmailov, Andrew Gordon Wilson
Improving Consistency-Based Semi-Supervised Learning with Weight Averaging. CoRR (2018)