Marc Anton Finzi
9 papers · 2021–2025 · 2 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(18)
🐣
Hot Topic Early Bird
🔥
Unstoppable · Bronze
Top co-authors
Research topics
Keywords
partial differential equation
(2)
neural network
(2)
generalization bound
(2)
convolutional neural network
(2)
large language model
(2)
learning rate
(1)
curse of dimensionality
(1)
dynamics modeling
(1)
dynamical system
(1)
diffusion model
(1)
kolmogorov complexity
(1)
score function
(1)
inductive bia
(1)
pre-trained model
(1)
ordinary differential equation
(1)
scaling law
(1)
quantization error
(1)
irregular sampling
(1)
conditional sampling
(1)
gaussian process
(1)
Papers
Compute-Optimal LLMs Provably Generalize Better with Scale
ICLR 2025
Compute Better Spent: Replacing Dense Layers with Structured Matrices
ICML 2024
Non-Vacuous Generalization Bounds for Large Language Models
ICML 2024
Position: The No Free Lunch Theorem, Kolmogorov Complexity, and the Role of Inductive Biases in Machine Learning
ICML 2024
A Stable and Scalable Method for Solving Initial Value PDEs with Neural Networks
ICLR 2023
The Lie Derivative for Measuring Learned Equivariance
ICLR 2023
User-defined Event Sampling and Uncertainty Quantification in Diffusion Models for Physical Dynamical Systems
ICML 2023
Deconstructing the Inductive Biases of Hamiltonian Neural Networks
ICLR 2022
Probabilistic Numeric Convolutional Neural Networks
ICLR 2021