Marc Finzi

9

Papers

60

Total Citations

Papers (9)

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

Non-Vacuous Generalization Bounds for Large Language Models

Compute Better Spent: Replacing Dense Layers with Structured Matrices

Simplifying Hamiltonian and Lagrangian Neural Networks via Explicit Constraints

Learning Invariances in Neural Networks from Training Data

Residual Pathway Priors for Soft Equivariance Constraints

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

Large Language Models Are Zero-Shot Time Series Forecasters

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