Dave Moore

I'm a PhD student in computer science, advised by Stuart Russell.

My primary current project is the application of Bayesian inference to nuclear weapons test monitoring: given seismic waveforms from a global network of stations, we want to infer a set of seismic events that plausibly explains the observed signals. Portions of this work have been funded by the CTBTO and DTRA.

I am also interested more generally in statistical machine learning, especially in probabilistic programming, i.e., tools and techniques allowing compact specification of and efficient general-purpose inference in complex probability models, and also in nonparametric Bayesian statistics, in particular Gaussian processes. I'm hopeful that these interests can advance the Project of AI.

Before coming to Berkeley, I was an undergrad at Williams College, where I majored in CS and math and wrote a senior thesis with Andrea Danyluk.

Email: dmoore@cs.berkeley.edu
Office: Sutardja Dai Hall, 7th floor, desk 108.
Calendar: here.


Research

Other work


Software

Note: please contact me if you plan to use any of this code! Some of it may be poorly documented or broken in its current form, but I'm glad to help figure out how it can be useful to you.

Matrizer is an optimizing compiler for linear algebra expressions: it tries to infer matrix properties and rewrite computations for efficient and numerically stable execution. Currently the main output target is NumPy. For example, the normal equations expression (X'X)^-1 X'y is transformed into Python code scipy.linalg.cho_solve(scipy.linalg.cho_factor(np.dot(X.T, X)), np.dot(X.T, y)).

The SparseGP package implements Gaussian process regression in Python, with efficient posterior calculations via cover trees as described in our UAI-MSTND paper above.


Teaching

I'm not currently teaching. Courses I've assisted with in the past:


Personal

In my spare time, I play violin with the UC Berkeley Symphony Orchestra. We play about one concert set per month during the academic year, with a wide range of great repertoire (see the website for details). Tickets are only $5 for Berkeley students, so come check us out!

If you're a Williams or Berkeley undergrad thinking about applying to CS grad schools, feel free to get in touch; I'm more than happy to talk about my experiences with the process! I can't guarantee to be helpful, but I can guarantee to be more helpful than either of these guys.

I've started a blog to contain writings on CS and non-CS topics. I'm not sure yet how often it'll be updated.