Scott Linderman
Assistant Professor at Stanford University
Palo Alto, California, United States
Summary
🤩
Rockstar🎓
Top SchoolScott Linderman is an assistant professor of Statistics at Stanford and a member of the Wu Tsai Neurosciences Institute who builds probabilistic models and scalable inference algorithms to decode complex biological data. With a PhD in Computer Science from Harvard and a postdoc at Columbia under Liam Paninski and David Blei, he blends rigorous machine learning theory with hands-on computational neuroscience. His twelve-year career spans academic research and industry engineering, including work at Microsoft, and he is a prolific open-source contributor to state-space and Bayesian nonparametrics tooling (notably contributions to pyhsmm and the JAX-based dynamax/ssm libraries). Scott’s work emphasizes practical algorithmic innovations — such as autoregressive HMMs and blocked-Gibbs samplers — that make sophisticated models usable on real neural datasets. Based in Palo Alto, he is equally comfortable writing core model code and translating statistical ideas into reproducible software.
12 years of coding experience
4 years of employment as a software developer
Ph.D., Computer Science, Ph.D., Computer Science at Harvard UniversityBS, Electrical and Computer Engineering, BS, Electrical and Computer Engineering at Cornell University
Github Skills (21)
bayesian-statistics10
python10
machine-learning10
numpy10
parameter-estimation10
bayesian10
state-space10
statistical-models10
hmmlearn10
jax10
autoregressive-models10
model-driven9
scipy9
distributions9
autograd9
Programming languages (6)
Github contributions (5)
probml/dynamax
Apr 2022 - Nov 2022
State Space Models library in JAX
Role in this project:
ML Engineer
ML EngineerContributions:17 releases, 60 reviews, 383 commits in 7 months
Contributions summary:Scott added code to the `ssm-jax` library, with a primary focus on implementing algorithms used in Hidden Markov Models and state space models. Their work included the implementation of autoregressive HMMs, a blocked-Gibbs sampler, and other functions that are useful for parameter estimation in these models. Their contributions also included documentation of the implemented algorithms, and the development of a class to fit parameters in the HMMs.
pythonstate-space-modelsdynamical-systemskalman-filterstate-space
lindermanlab/ssm
Jun 2018 - Oct 2022
Bayesian learning and inference for state space models
Role in this project:Back-end Developer
Back-end DeveloperContributions:7 reviews, 337 commits, 55 PRs in 4 years 5 months
Contributions summary:Scott primarily contributed to the core implementation of the hidden Markov models, autoregressive models and state space models. The user implemented new variants of HMMs, including input-driven and recurrent versions. Key contributions are evident in the development of essential modules like `models.py`, suggesting expertise in the core algorithms and mathematical formulations underlying state space models.
state-space-modelsbayesian-inferenceinferencestate-spacejulia
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.