John Thickstun

Contact: thickstn at

I am a PhD student in Computer Science & Engineering at the University of Washington, co-advised by Sham Kakade and Zaid Harchaoui. My current research interests include representation learning, time series models, structured prediction, and applications to music.

My CV/resume is available here.

The MusicNet Dataset

Publications and Preprints

Coupled Recurrent Models for Polyphonic Music Composition.
John Thickstun, Zaid Harchaoui, Dean P. Foster, and Sham M. Kakade.
ArXiv preprint, 2018.

Invariances and Data Augmentation for Supervised Music Transcription.
John Thickstun, Zaid Harchaoui, Dean P. Foster, and Sham M. Kakade.
International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2018.
Experiments available on GitHub.

Learning Features of Music from Scratch.
John Thickstun, Zaid Harchaoui, and Sham M. Kakade.
International Conference on Learning Representations (ICLR), 2017.
Experiments available on GitHub.

Notes and Tutorials

Conditional Random Fields as a generalization of logistic regression

Some notes on Hilbert-Schmidt operators

Heuristics for manipulating stochastic differential equations

Estimating the Shannon capacity of a graph

Kernels and Mercer's Theorem

Thoughts on proof assistants with companion code


Three perspectives on the Black-Scholes formula:

Negative probabilities in the binomial option pricing model


The fast Johnson-Lindenstrauss transform

The coin flip martingale

Probability densities from a measure-theoretic perspective

Change of measure

Fun stuff

Some linguistic observations

The dangers of blindly changing variables

Quotient sigma-algebras

Climbing a tower of abstractions