Chris Yeh
AI for Sustainability | PhD Candidate @ Caltech
I am a final-year PhD candidate in Computing and Mathematical Sciences (CMS) at Caltech, where I develop AI algorithms for decision-making under uncertainty with applications in energy, sustainability, and science. I am advised by professors Yisong Yue and Adam Wierman, and my research is generously supported by the Caltech Resnick Sustainability Institute and the Quad Fellowship. I have also been supported by a Caltech AI4Science/Amazon AWS Fellowship.
Previously, I studied Computer Science at Stanford where I was a member of the Sustainability and AI Lab and served as president of Code the Change. I also spent a year studying global affairs as a Schwarzman Scholar at Tsinghua in Beijing.
Selected publications
For a complete list of my publications, see my publications page. * denotes equal contribution
-
Conformal Risk Training: End-to-end optimization of conformal risk control
C. Yeh, N. Christianson, A. Wierman, Y. Yue
NeurIPS 2025C. Yeh, N. Christianson, A. Wierman, and Y. Yue, “Conformal Risk Training: End-to-end optimization of conformal risk control,” in Advances in Neural Information Processing Systems, vol. 38, San Diego, CA, USA, Dec. 2025.
title = {{Conformal Risk Training: End-to-end optimization of conformal risk control}}, author = {Yeh, Christopher and Christianson, Nicolas and Wierman, Adam and Yue, Yisong}, year = 2025, month = dec, booktitle = {Advances in Neural Information Processing Systems}, address = {San Diego, CA, USA}, volume = 38 } -
Maximizing the Value of Predictions in Control: Accuracy Is Not Enough
Y. Lin, Z. Chen, C. Yeh, A. Wierman
NeurIPS 2025Y. Lin, Z. Chen, C. Yeh, and A. Wierman, “Maximizing the Value of Predictions in Control: Accuracy Is Not Enough,” in Advances in Neural Information Processing Systems, vol. 38, San Diego, CA, USA, Dec. 2025.
title = {{Maximizing the Value of Predictions in Control: Accuracy Is Not Enough}}, author = {Lin, Yiheng and Chen, Zaiwei and Yeh, Christopher and Wierman, Adam}, year = 2025, month = dec, booktitle = {Advances in Neural Information Processing Systems}, address = {San Diego, CA, USA}, volume = 38 } -
End-to-End Conformal Calibration for Optimization Under Uncertainty
C. Yeh*, N. Christianson*, A. Wu, A. Wierman, Y. Yue
PreprintC. Yeh, N. Christianson, A. Wu, A. Wierman, and Y. Yue, End-to-end conformal calibration for optimization under uncertainty, 2024. DOI: 10.48550/arXiv.2409.20534. [Online]. Available: https://arxiv.org/abs/2409.20534.
title = {End-to-End Conformal Calibration for Optimization Under Uncertainty}, author = {Yeh, Christopher and Christianson, Nicolas and Wu, Alan and Wierman, Adam and Yue, Yisong}, year = 2024, doi = {10.48550/arXiv.2409.20534}, url = {https://arxiv.org/abs/2409.20534} } -
Online learning for robust voltage control under uncertain grid topology
C. Yeh, J. Yu, Y. Shi, A. Wierman
IEEE Transactions on Smart Grid, September 2024C. Yeh, J. Yu, Y. Shi, and A. Wierman, “Online learning for robust voltage control under uncertain grid topology,” IEEE Transactions on Smart Grid, vol. 15, no. 5, pp. 4754-4764, Sep. 2024, ISSN: 1949-3061. DOI: 10.1109/TSG.2024.3383804. [Online]. Available: https://ieeexplore.ieee.org/document/10486962.
title = {Online Learning for Robust Voltage Control Under Uncertain Grid Topology}, author = {Yeh, Christopher and Yu, Jing and Shi, Yuanyuan and Wierman, Adam}, year = 2024, month = 9, journal = {IEEE Transactions on Smart Grid}, volume = 15, number = 5, pages = {4754--4764}, doi = {10.1109/TSG.2024.3383804}, issn = {1949-3061}, url = {https://ieeexplore.ieee.org/document/10486962} } -
SustainGym: Reinforcement Learning Environments for Sustainable Energy Systems
C. Yeh, V. Li, R. Datta, J. Arroyo, N. Christianson, C. Zhang, Y. Chen, M. Hosseini, A. Golmohammadi, Y. Shi, Y. Yue, and A. Wierman
NeurIPS 2023 Datasets and Benchmarks TrackPDF Project Page Poster Code Cite
C. Yeh, V. Li, R. Datta, J. Arroyo, N. Christianson, C. Zhang, Y. Chen, M. Hosseini, A. Golmohammadi, Y. Shi, Y. Yue, and A. Wierman, “SustainGym: A Benchmark Suite of Reinforcement Learning for Sustainability Applications,” in Thirty-seventh Conference on Neural Information Processing Systems Datasets and Benchmarks Track, New Orleans, LA, USA, Dec. 2023. [Online]. Available: https://openreview.net/forum?id=vZ9tA3o3hr.
title = {{SustainGym}: Reinforcement Learning Environments for Sustainable Energy Systems}, author = {Yeh, Christopher and Li, Victor and Datta, Rajeev and Arroyo, Julio and Zhang, Chi and Chen, Yize and Hosseini, Mehdi and Golmohammadi, Azarang and Shi, Yuanyuan and Yue, Yisong and Wierman, Adam}, year = 2023, month = dec, booktitle = {Advances in Neural Information Processing Systems}, publisher = {Curran Associates, Inc.}, address = {New Orleans, LA, USA}, volume = 36, pages = {59464--59476}, url = {https://proceedings.neurips.cc/paper_files/paper/2023/hash/ba74855789913e5ed36f87288af79e5b-Abstract-Datasets_and_Benchmarks.html} }
Upcoming events
-
Cornell Young Researchers Workshop
I will present a poster on “Learning Decision-Focused Uncertainty Representations” at the Cornell Young Researchers Workshop hosted at Cornell University in Ithaca, New York.
-
INFORMS Annual Meeting 2025
I have been invited to present my work on “Learning Decision-Focused Uncertainty Representations for Robust and Risk-Constrained Optimization” at the Energy and Applied Probability Session of the 2025 INFORMS Annual Meeting in Atlanta, Georgia. Thank you Professor Gal Mendelson for the invitation!
-
NeurIPS 2025
I will be presenting two conference papers at NeurIPS 2025 and two workshop papers at the NeurIPS 2025 Workshop on Tackling Climate Change with Machine Learning. Check my publications page for more details!
-
Caltech 2025-26 Science Journeys speaker
I am selected as one of 3 speakers for the Caltech Science Journeys series for the 2025-26 season. I will give a public lecture on my research in AI for sustainability in Beckman Auditorium.
Recent news
-
Awarded Quad Fellowship
I am among 37 graduate students (5 in USA) selected for the 2025 Quad Fellowship, and I am featured in Caltech News. The Quad Fellowship is an initiative of the governments of The Quad countries (Australia, India, Japan, USA) to build ties among the next generation of STEM leaders.
-
Served as Panelist for UNC CLAIM Workshop
I served as a panelist a session titled “AI - Buzzword or Breakthrough Technology?” for the Center for Climate Leadership and AI-driven Integrity and Mitigation (CLAIM) Workshop at the University of North Carolina at Chapel Hill. Thank you Professor Angel Hsu for the invitation!
-
Presented at ICCOPT 2025
I gave a talk on “Learning Decision-Focused Uncertainty Representations for Robust and Risk-Constrained Optimization” at the 2025 International Conference on Continuous Optimization (ICCOPT), hosted at the University of Southern California in Los Angeles, California.
-
Presented at MIT Professor Priya Donti's Group Meeting
I was invited to present my work on “End-to-end Conformal Calibration for Risk Control and Robust Optimization” at a group meeting of Professor Priya Donti’s group at MIT. Thank you Professor Donti for the inviation!
-
Presented at 2025 SoCal OR/OM Day
I was invited to present my work on “End-to-End Conformal Calibration for Robust Grid-Scale Battery Storage Optimization” at the 2025 SoCal OR/OM Day hosted at the UC Irvine Paul Merage School of Business.
-
Awarded Best Reviewer for AISTATS 2025
I am one of 126 reviewers out of 3120 total reviewers to receive the AISTATS 2025 Best Reviewer Award.
-
Presented at Johns Hopkins Junior MINDS Seminar
I gave a talk titled “End-to-end conformal calibration for optimization under uncertainty” at the Johns Hopkins Junior MINDS (Mathematical Institute for Data Science) Seminar. Thank you Professor Anqi Liu for the invitation!
-
Awarded best student presentation at the Business Analytics, Artificial Intelligence, and Cherry Blossom Conference at Johns Hopkins
I was awarded best student presentation (out of 8 presenters) for my talk on “End-to-end conformal calibration for optimization under uncertainty” at the Business Analytics, Artificial Intelligence, and Cherry Blossom Conference at Johns Hopkins Carey Business School.
Selected Awards and Honors
Quad Fellow
I am among 37 graduate students (5 in USA) selected for the 2025 Quad Fellowship, and I am featured in Caltech News. The Quad Fellowship is an initiative of the governments of The Quad countries (Australia, India, Japan, USA) to build ties among the next generation of STEM leaders.
Best Reviewer for AISTATS 2025
I am one of 126 reviewers out of 3120 total reviewers to receive the AISTATS 2025 Best Reviewer Award.
Best Student Presentation at the Business Analytics, Artificial Intelligence, and Cherry Blossom Conference at Johns Hopkins
I was awarded best student presentation (out of 8 presenters) for my talk on “End-to-end conformal calibration for optimization under uncertainty” at the Business Analytics, Artificial Intelligence, and Cherry Blossom Conference at Johns Hopkins Carey Business School.
OpenMinds NextGen Leader
I am one of 32 graduate students selected for the OpenMinds NextGen Leaders program. OpenMinds is a non-profit organization building a network of leaders to tackle the dual challenges of more energy, less emissions, fast.
Honorable Mention, Best Poster Award at LANL Grid Science Winter School
I received an honorable mention for best poster award for my poster on “End-to-end conformal calibration for robust grid-scale battery storage optimization” at the 2025 LANL Grid Science Winter School hosted at Los Alamos National Laboratory.
Thomas A. Tisch Prize for Graduate Teaching in CMS
This prive is awarded to 1 Caltech CMS department graduate teaching assistant each year.
Best Paper Finalist, ACM e-Energy Conference
Our paper, “Robust online voltage control with an unknown grid topology,” was selected as one of 3 best paper finalists (out of 35 accepted papers) at the 2022 ACM e-Energy Conference.
Amazon/Caltech AI4Science Fellow
The AI4Science Fellows program is a result of a partnership between Caltech and Amazon around machine learning and artificial intelligence. The program recognizes graduate students and postdoctoral scholars that have had a remarkable impact in these areas, and in their application to fields beyond computer science.
Schwarzman Scholar
I was among 147 Schwarzman Scholars selected from over 2,800 applicants from 38 countries for the 4th cohort of the Schwarzman Scholars program at Tsinghua University in Beijing, China.
Featured Posts
-
controlenergy
Simplified DistFlow Equations
Recently, I worked on the voltage control problem for radial distribution grids (see here). More simply, the problem is to keep voltages in an electric grid within a fixed range at all locations in the grid, under the assumption that the grid is radial, meaning tree-structured. Like most other voltage control algorithms, I used the linear “Simplified DistFlow” model. It took me a while to understand the math behind this model, and I hope this post demystifies some of that complexity.
-
math
Schur Complements and the Matrix Inversion Lemma
I prove key properties of Schur Complements and use them to derive the matrix inversion lemma.
-
ML
An Overview of k-way Spectral Clustering
Given an undirected graph \(G = (V, E)\), a common task is to identify clusters among the nodes. It is a well-known fact that the sign of entries in the second eigenvector of the normalized Graph Laplacian matrix provides a convenient way to partition the graph into two clusters; this “spectral clustering” method has strong theoretical foundations. In this post, I highlight several theoretical works that generalize the technique for \(k\)-way clustering.
-
python
The Definitive Guide to Python import Statements
I’ve almost never been able to write correct Python
importstatements on the first go. Behavior is inconsistent between Python 2.7 and Python 3.6 (the two versions that I test here), and there is no single method for guaranteeing that imports will always work. This post is my dive into how to resolve common importing problems. Unless otherwise stated, all examples here work with both Python 2.7 and 3.6.