John J. Vastola

According to our database, John J. Vastola authored at least 8 papers between 2022 and 2025.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of five.

2025

Deep RL Needs Deep Behavior Analysis: Exploring Implicit Planning by Model-Free Agents in Open-Ended Environments.

Riley Simmons-Edler, Ryan Paul Badman, Felix Baastad Berg, Raymond Chua, John J. Vastola, Joshua Lunger, William Qian, Kanaka Rajan

CoRR, June, 2025

Dynamical symmetries in the fluctuation-driven regime: an application of Noether's theorem to noisy dynamical systems.

John J. Vastola

CoRR, April, 2025

Generalization through variance: how noise shapes inductive biases in diffusion models.

John J. Vastola

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

2024

The Unreasonable Effectiveness of Gaussian Score Approximation for Diffusion Models and its Applications.

Binxu Wang, John J. Vastola

Trans. Mach. Learn. Res., 2024

2023

The Hidden Linear Structure in Score-Based Models and its Application.

Binxu Wang, John J. Vastola

CoRR, 2023

Diffusion Models Generate Images Like Painters: an Analytical Theory of Outline First, Details Later.

Binxu Wang, John J. Vastola

CoRR, 2023

Optimal packing of attractor states in neural representations.

John J. Vastola

Proceedings of the NeurIPS Workshop on Symmetry and Geometry in Neural Representations, 2023

2022

Is the information geometry of probabilistic population codes learnable?

John J. Vastola, Zach Cohen, Jan Drugowitsch

Proceedings of the NeurIPS Workshop on Symmetry and Geometry in Neural Representations, 2022