OpenReview
.net
OpenReview
.net
Login
OpenReview
.net
Login
John J. Vastola
Postdoc, Neurobiology, Harvard Medical School
Joined
May 2022
Names
John J. Vastola
(Preferred)
,
John Vastola
Emails
****@hms.harvard.edu
(Confirmed)
Personal Links
Homepage
Google Scholar
DBLP
ORCID
Career & Education History
Postdoc
Neurobiology,
Harvard Medical School
(hms.harvard.edu)
2021
–
Present
PhD student
Physics,
Vanderbilt University
(vanderbilt.edu)
2016
–
2021
Advisors, Relations & Conflicts
Postdoc Advisor
Samuel J. Gershman
2025
–
Present
Postdoc Advisor
Kanaka Rajan
2025
–
Present
Postdoc Advisor
Jan Drugowitsch
2021
–
2025
PhD Advisor
William R. Holmes
2017
–
2021
Expertise
diffusion models
2023
–
Present
computational neuroscience
2021
–
Present
Publications
Storing long-lived memories via molecular error correction: a minimal mathematical model of Crick’s memory switch
John J. Vastola
,
Tejas Ramdas
,
Samuel J. Gershman
Crossref
Readers:
Everyone
Monod: model-based discovery and integration through fitting stochastic transcriptional dynamics to single-cell sequencing data
Gennady Gorin
,
Tara Chari
,
Maria Carilli
,
John J. Vastola
,
Lior Pachter
Crossref
Readers:
Everyone
A Variational Manifold Embedding Framework for Nonlinear Dimensionality Reduction
John J. Vastola
,
Samuel J. Gershman
,
Kanaka Rajan
NeurReps 2025 Proceedings
Readers:
Everyone
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 Vastola
,
Joshua Lunger
,
William Qian
,
Kanaka Rajan
NeurIPS 2025 poster
Readers:
Everyone
Gradient Descent as Loss Landscape Navigation: a Normative Framework for Deriving Learning Rules
John Vastola
,
Samuel J. Gershman
,
Kanaka Rajan
NeurIPS 2025 poster
Readers:
Everyone
Generalization through variance: how noise shapes inductive biases in diffusion models
John Vastola
ICLR 2025 Poster
Readers:
Everyone
Dynamical symmetries in the fluctuation-driven regime: an application of Noether's theorem to noisy dynamical systems
John Vastola
NeurReps 2024 Poster
Readers:
Everyone
The Unreasonable Effectiveness of Gaussian Score Approximation for Diffusion Models and its Applications
Binxu Wang
,
John Vastola
Accepted by TMLR
Readers:
Everyone
Optimal packing of attractor states in neural representations
John Vastola
NeurReps 2023 Poster
Readers:
Everyone
High variance score function estimates help diffusion models generalize
John Vastola
Submitted to ICLR 2024
Readers:
Everyone
View all 15 publications
Co-Authors
Binxu Wang
Felix Baastad Berg
Gennady Gorin
Jan Drugowitsch
Joshua Lunger
Kanaka Rajan
Lior Pachter
Maria Carilli
Meichen Fang
Raymond Chua
Riley Simmons-Edler
Ryan Paul Badman
Samuel J. Gershman
Tara Chari
Tejas Ramdas
William Qian
Zach Cohen