Marc Finzi

Most-cited papers

Large Language Models Are Zero-Shot Time Series Forecasters
N. Gruver, Marc Finzi, Shikai Qiu, Andrew Gordon Wilson
2023Neural Information Processing Systems926 citations Open access
Semantic Scholar
Generalizing Convolutional Neural Networks for Equivariance to Lie Groups on Arbitrary Continuous Data
Marc Finzi, S. Stanton, Pavel Izmailov, A. Wilson
2020International Conference on Machine Learning410 citations
Semantic Scholar
There Are Many Consistent Explanations of Unlabeled Data: Why You Should Average
Ben Athiwaratkun, Marc Finzi, Pavel Izmailov, A. Wilson
2018International Conference on Learning Representations264 citations
Semantic Scholar
A Practical Method for Constructing Equivariant Multilayer Perceptrons for Arbitrary Matrix Groups
Marc Finzi, M. Welling, A. Wilson
2021International Conference on Machine Learning252 citations
Semantic Scholar
Simplifying Hamiltonian and Lagrangian Neural Networks via Explicit Constraints
Marc Finzi, K. Wang, A. Wilson
2020Neural Information Processing Systems171 citations
Semantic Scholar
Semi-Supervised Learning with Normalizing Flows
Pavel Izmailov, P. Kirichenko, Marc Finzi, A. Wilson
2019International Conference on Machine Learning144 citations
Semantic Scholar
PAC-Bayes Compression Bounds So Tight That They Can Explain Generalization
Sanae Lotfi, Marc Finzi, Sanyam Kapoor, Andres Potapczynski +2 more
2022Neural Information Processing Systems102 citations Open access
Semantic Scholar
Residual Pathway Priors for Soft Equivariance Constraints
Marc Finzi, Gregory W. Benton, A. Wilson
2021Neural Information Processing Systems90 citations
Semantic Scholar
The No Free Lunch Theorem, Kolmogorov Complexity, and the Role of Inductive Biases in Machine Learning
Micah Goldblum, Marc Finzi, K. Rowan, A. Wilson
2023International Conference on Machine Learning83 citations Open access
Semantic Scholar
Learning Invariances in Neural Networks
Gregory W. Benton, Marc Finzi, Pavel Izmailov, A. Wilson
2020Neural Information Processing Systems79 citations
Semantic Scholar
The Lie Derivative for Measuring Learned Equivariance
N. Gruver, Marc Finzi, Micah Goldblum, A. Wilson
2022International Conference on Learning Representations72 citations Open access
Semantic Scholar
Non-Vacuous Generalization Bounds for Large Language Models
Sanae Lotfi, Marc Finzi, Yilun Kuang, Tim G. J. Rudner +2 more
2023International Conference on Machine Learning67 citations
Semantic Scholar
Deconstructing the Inductive Biases of Hamiltonian Neural Networks
N. Gruver, Marc Finzi, S. Stanton, A. Wilson
2022International Conference on Learning Representations52 citations
Semantic Scholar
From Entropy to Epiplexity: Rethinking Information for Computationally Bounded Intelligence
Marc Finzi, Shikai Qiu, Yiding Jiang, Pavel Izmailov +2 more
2026arXiv.org47 citations
Semantic Scholar
User-defined Event Sampling and Uncertainty Quantification in Diffusion Models for Physical Dynamical Systems
Marc Finzi, Anudhyan Boral, A. Wilson, F. Sha +1 more
2023International Conference on Machine Learning40 citations Open access
Semantic Scholar
Compute Better Spent: Replacing Dense Layers with Structured Matrices
Shikai Qiu, Andres Potapczynski, Marc Finzi, Micah Goldblum +1 more
2024International Conference on Machine Learning37 citations
Semantic Scholar
Improving Consistency-Based Semi-Supervised Learning with Weight Averaging
Ben Athiwaratkun, Marc Finzi, Pavel Izmailov, A. Wilson
2018arXiv.org36 citations
Semantic Scholar
Unlocking Tokens as Data Points for Generalization Bounds on Larger Language Models
Sanae Lotfi, Yilun Kuang, Brandon Amos, Micah Goldblum +2 more
2024Neural Information Processing Systems29 citations
Semantic Scholar
Effective Surrogate Models for Protein Design with Bayesian Optimization
N. Gruver, S. Stanton, P. Kirichenko, Marc Finzi +5 more
202122 citations
Semantic Scholar
Invertible Convolutional Networks
Marc Finzi, Pavel Izmailov, Wesley J. Maddox, P. Kirichenko +1 more
201922 citations
Semantic Scholar
A Stable and Scalable Method for Solving Initial Value PDEs with Neural Networks
Marc Finzi, Andres Potapczynski, M. Choptuik, A. Wilson
2023International Conference on Learning Representations21 citations Open access
Semantic Scholar
CoLA: Exploiting Compositional Structure for Automatic and Efficient Numerical Linear Algebra
Andres Potapczynski, Marc Finzi, Geoff Pleiss, Andrew Gordon Wilson
2023Neural Information Processing Systems14 citations Open access
Semantic Scholar
Probabilistic Numeric Convolutional Neural Networks
Marc Finzi, Roberto Bondesan, M. Welling
2020International Conference on Learning Representations14 citations
Semantic Scholar
Searching for Efficient Linear Layers over a Continuous Space of Structured Matrices
Andres Potapczynski, Shikai Qiu, Marc Finzi, C. Ferri +5 more
2024Neural Information Processing Systems12 citations
Semantic Scholar
SKIing on Simplices: Kernel Interpolation on the Permutohedral Lattice for Scalable Gaussian Processes
Sanyam Kapoor, Marc Finzi, K. Wang, A. Wilson
2021International Conference on Machine Learning12 citations
Semantic Scholar
Compute-Optimal LLMs Provably Generalize Better with Scale
Marc Finzi, Sanyam Kapoor, Diego Granziol, An-Ming Gu +3 more
2025International Conference on Learning Representations10 citations
Semantic Scholar
Requential Coding: Pushing the Limits of Model Compression with Self-Generated Training Data
Shikai Qiu, Marc Finzi, Yujia Zheng, Kun Zhang +1 more
2026arXiv.org1 citations
Semantic Scholar
Understanding and Incorporating Mathematical Inductive Biases in Neural Networks
Marc Finzi
20231 citations
Semantic Scholar