Selected Papers | Mentoring | Projects | Google Scholar | GitHub

Hi! I’m a 5th year PhD student in Statistics at the University of Michigan, where I focus on uncertainty quantification, robust decision-making, and AI for Science, advised by Ambuj Tewari. I have significant prior experience with C++, Python/PyTorch, OpenGL/GLSL, OpenCL, and Unity. My research interest centers around one core question:

How can we design principled uncertainty estimates for black-box models and use such uncertainty optimally for decision-making?

During my PhD, I have interned at Waymo under Aman Sinha on distributed convex optimization for optimal importance sampling of rare events and at Bose under Shuo Zhang and Russell Izadi on reinforcement learning for adaptive noise cancellation.

Prior to my PhD, I was a senior software engineer (IC5) at Meta from 2018-2021, where I worked on computer vision and graphics for realtime dense 3D reconstruction (point clouds/KinectFusion) and dynamic real-time disocclusion on meshes. I also implemented, trained, and optimized (with layer fusion, SNPE, and QAT quantization) an end-to-end deep learning-based feature for Portal to run at realtime on the Snapdragon SoC.

Before working at Meta, I graduated as a math major from Princeton in 2018 with certificates in CS and Statistics/ML, where my senior thesis focused on adversarial behaviors on blockchain networks and was advised by Matt Weinberg. See my full resume here.

Selected Papers

---

My work has largely focused on developing methods with end-to-end statistical guarantees to create reliable machine learning systems and layering robust decision-making on top of such uncertainty estimates, especially for scientific applications. My projects largely split into three headings: uncertainty quantification methodology, robust decision-making, and AI for Science.

Uncertainty Quantification Methodology

Conformal Prediction for Ensembles: Improving Efficiency via Score-Based Aggregation
Neural Information Processing Systems (NeurIPS), 2025
Rivera, E.O.*, Patel, Y.* (* equal contribution), Tewari, A.
[Paper] [GitHub]

Variational Inference with Coverage Guarantees in Simulation-Based Inference
International Conference on Machine Learning (ICML), 2024
Patel, Y., McNamara, D., Loper, J., Regier, J., Tewari, A.
[Paper] [GitHub]

Robust Decision-Making

Conformal Contextual Robust Optimization
International Conference on Artificial Intelligence and Statistics (AISTATS), 2024 (Oral)
Patel, Y., Rayan, S., Tewari, A.
[Paper] [GitHub]

Conformal Robust Control of Linear Systems
In Submission
Patel, Y., Rayan, S., Tewari, A.
[Paper] [GitHub]

Non-Parameteric Conformal Distributionally Robust Optimization
ICML Workshop on Structured Probabilistic Inference & Generative Modeling, 2024
Patel, Y., Cao, G., Tewari, A.
[Workshop Paper]

AI for Science

Continuum Transformers Perform In-Context Learning by Operator Gradient Descent
Neural Information Processing Systems (NeurIPS), 2025
ICLR AI for Accelerated Materials Design Workshop, 2025
Patel, Y.*, Mishra, A.* (* equal contribution), Tewari, A.
[Paper] [GitHub]

Operator Learning for Schrödinger Equation: Unitarity, Error Bounds, and Time Generalization
In Submission
Patel, Y.*, Subedi, U.* (* equal contribution), Tewari, A.
[Paper] [GitHub]

Diffusion Models for Probabilistic Deconvolution of Galaxy Images
ICML Machine Learning for Astrophysics Workshop, 2023
Li, Y., Xue, Z., Patel, Y., Regier, J.
[Workshop Paper] [GitHub]

RL Boltzmann Generators for Conformer Generation in Data-Sparse Environments
NeurIPS Machine Learning in Structural Biology (MLSB) Workshop, 2022
Patel, Y., Tewari, A.
[Workshop Paper] [GitHub]

Scalable Bayesian Inference for Finding Strong Gravitational Lenses
NeurIPS Machine Learning and the Physical Sciences Workshop, 2022
Patel, Y., Regier, J.
[Workshop Paper] [GitHub]

Patents

Holographic Calling for Artificial Reality
US Patent App. 17/360,693
AP Pozo, J Virskus, G Venkatesh, K Li, SC Chen, A Kumar, R Ranjan, BK Cabral, SA Johnson, W Ye, MA Snower, Y Patel.
[Patent]

---

Mentoring

During my PhD, I have also had the opportunity to mentor the following fantastic undergraduate and master’s students on their theses and research projects.

Guyang (Kevin) Cao (Next step: Ph.D. in Computer Science at University of Wisconsin-Madison)
Honors Thesis, 2023-24
Undergraduate Research Program in Statistics, 2023
Non-parametric Conformal Distributionally Robust Optimization

Zhiwei Xue (Next step: Ph.D. in Computer Science at National University of Singapore)
Undergraduate Research Program in Statistics, 2023
Diffusion Models for Probabilistic Deconvolution of Galaxy Images

Yuhang Li (Next step: Master’s in Computer Science at University of Illinois, Urbana-Champaigna)
Undergraduate Research Program in Statistics, 2023
Diffusion Models for Probabilistic Deconvolution of Galaxy Images

Zhong Zheng (Next step: Master’s in Computational Data Science at Carnegie Mellon University)
Undergraduate Research Program in Statistics, 2023
Atomic Maps Reconstruction for Cryo-EM Data with Continuous Heterogeneity

---

Highlighted Projects

Outside of my formal research projects, I have worked on a wide spread of projects, spanning multi-armed bandits, computational fluid dynamics, and importance sampling for rendering. Here are some highlights.

Multiple Importance Sampling in Light Transport
University of Michigan Project, 2021
[Project Report] [GitHub]

HyperLoop Pod Design
Princeton University Project Founder & Lead, 2015-2017
2x Top 30 Team, International SpaceX HyperLoop Pod Design Competition
[Project Report]

Tesla Autopilot Analysis
Princeton University Project, 2016
[Project Report]

Deanonymizing Bitcoin Transactions: An Investigative Study On Large-scale Graph Clustering
Princeton University Senior Thesis, 2018
[Project Report]

---

Miscellaneous

Outside of research, I really enjoy lifting and reading. If you want to contact me, please reach out at yppatel [at] umich.edu!