Sotabase

Career

· Machine Learning Scientist, Lila Sciences2024–
· Ph.D. in Machine Learning, Carnegie Mellon University2018–2024
· Intern, Google2017–2017
· Internship Software Engineer, Skybox Imaging2016–2016
· Intern, Terra Bella (Google)2016–2016
· Learning Assistant (APPM 4350 Fourier Series & Boundary Value Problems), University of Colorado Boulder2016–2016
· Research Assistant, University of Colorado Boulder2015–2016
· M.S./B.S. in Applied Math and B.S. in Computer Science, University of Colorado Boulder2013–2018

Publications (20)

Beyond Pinball Loss: Quantile Methods for Calibrated Uncertainty Quantification
Neural Information Processing Systems · 2020
114
cited
Uncertainty Toolbox: an Open-Source Library for Assessing, Visualizing, and Improving Uncertainty Quantification
arXiv.org · 2021
84
cited
Offline Contextual Bayesian Optimization
Neural Information Processing Systems · 2019
53
cited
Neural Dynamical Systems: Balancing Structure and Flexibility in Physical Prediction
IEEE Conference on Decision and Control · 2020
30
cited
How Useful are Gradients for OOD Detection Really?
arXiv.org · 2022
28
cited
DIII-D research advancing the physics basis for optimizing the tokamak approach to fusion energy
Nuclear Fusion · 2021
25
cited
Offline Model-Based Reinforcement Learning for Tokamak Control
Conference on Learning for Dynamics & Control · 2023
25
cited
Offline Contextual Bayesian Optimization for Nuclear Fusion
arXiv.org · 2020
14
cited
Toward a non-intrusive, physio- behavioral biometric for smartphones
International Conference on Human-Computer Interaction with Mobile Devices and Services · 2014
13
cited
Full Shot Predictions for the DIII-D Tokamak via Deep Recurrent Networks
arXiv.org · 2024
9
cited
BATS: Best Action Trajectory Stitching
arXiv.org · 2022
8
cited
Deep Attentive Variational Inference
International Conference on Learning Representations · 2022
8
cited
Exploration via Planning for Information about the Optimal Trajectory
Neural Information Processing Systems · 2022
8
cited
Automated experimental design of safe rampdowns via probabilistic machine learning
Nuclear Fusion · 2024
7
cited
Near-optimal Policy Identification in Active Reinforcement Learning
International Conference on Learning Representations · 2022
7
cited
PID-Inspired Inductive Biases for Deep Reinforcement Learning in Partially Observable Control Tasks
Neural Information Processing Systems · 2023
7
cited
Sampling-based Multi-dimensional Recalibration
International Conference on Machine Learning · 2024
3
cited
Algorithmic Construction and Stochastic Analysis of Optimal Automata for Generalized Strings
2018
1
cited
N EURAL D YNAMICAL S YSTEMS
2020
Stochastic Analysis of Minimal Automata Growth for Generalized Strings
Methodology and Computing in Applied Probability · 2019
Sotabase
Ian Char | Researcher Profile | Sotabase | Sotabase