Spencer Compton
comptons [at] stanford [dot] edu
comptons [at] stanford [dot] edu
I am a third-year PhD student in the CS theory group at Stanford, advised by the wonderful duo of Tselil Schramm and Gregory Valiant. I mostly work on theoretical computer science research involving algorithm design, information theory, and statistics. Please feel free to reach out!
I previously completed my undergrad/masters at MIT, where I had the privilege of being advised by Ronitt Rubinfeld and collaborating with IBM Research.
My research is generously supported by an NDSEG Fellowship.
Research (Google Scholar)
* denotes alphabetical ordering
Lower Bounds for Greedy Teaching Set Constructions
Spencer Compton*, Chirag Pabbaraju*, Nikita Zhivotovskiy*
COLT 2025
Attainability of Two-Point Testing Rates for Finite-Sample Location Estimation
Spencer Compton*, Gregory Valiant*
Preprint
Embedding Probability Distributions into Low Dimensional L₁: Tree Ising Models via Truncated Metrics
Moses Charikar*, Spencer Compton*, Chirag Pabbaraju*
SODA 2025
Near-Optimal Mean Estimation with Unknown, Heteroskedastic Variances
Spencer Compton*, Gregory Valiant*
STOC 2024
Computing Low-Entropy Couplings for Large-Support Distributions
Samuel Sokota, Dylan Sam, Christian Schroeder de Witt, Spencer Compton, Jakob Foerster, J. Zico Kolter
UAI 2024
Minimum-Entropy Coupling Approximation Guarantees Beyond the Majorization Barrier
Spencer Compton, Dmitriy Katz, Benjamin Qi, Kristjan Greenewald, Murat Kocaoglu
AISTATS 2023
New Partitioning Techniques and Faster Algorithms for Approximate Interval Scheduling
Spencer Compton*, Slobodan Mitrović*, Ronitt Rubinfeld*
ICALP 2023; Algorithmica
A Tighter Approximation Guarantee for Greedy Minimum Entropy Coupling
Spencer Compton
ISIT 2022 (Student Paper Award)
Entropic Causal Inference: Graph Identifiability
Spencer Compton, Kristjan Greenewald, Dmitriy Katz, Murat Kocaoglu
ICML 2022
Entropic Causal Inference: Identifiability and Finite Sample Results
Spencer Compton, Murat Kocaoglu, Kristjan Greenewald, Dmitriy Katz
NeurIPS 2020