News
 I (successfully!) defended my PhD in August 2018.
 We posted a preprint of our paper on promoting cooperation / competition via information regularization.
 Matt Botvinick presented our work on using the (variational) information bottleneck to promote good hierarchical policies for RL agents at the Hierarchical RL Workshop at NIPS 2017.
 I spent JuneOctober, 2017 interning at DeepMind with Matt Botvinick.

Research
I'm interested in reinforcement learning (RL), information theory, and deep learning with an eye toward understanding and creating intelligent agents. Much of my work has focused on the information bottleneck (IB) and lately I've been interested in using IB to improve the training of RL agents. In the past, I've also worked on quantum information theory and computational neuroscience.


Learning to Share and Hide Intentions using Information Regularization
DJ Strouse,
Max KleimanWeiner,
Josh Tenenbaum,
Matt Botvinick,
David Schwab
in progress
arXiv /
code
We train agents to cooperate / compete by regularizing the rewardrelevant information they share with other agents, enabling agents trained alone to nevertheless perform well in a multiagent setting.


Hierarchical reinforcement learning via variational information minimization
DJ Strouse,
Jane Wang,
Neil Rabinowitz,
David Pfau,
Matt Botvinick
in progress
talk /
note on Distral
We encourage RL agents to develop efficient hierarchical representations of task structure in a multigoal environment by limiting the information about the goal that is used by the policy.


Efficient use of discrete latent variables using the deterministic information bottleneck
DJ Strouse,
David Schwab
in progress
note
We use the deterministic information bottleneck to regularize discrete latent variable models, encouraging the use of as few latent variables as possible for a given level of performance.


The information bottleneck and geometric clustering
DJ Strouse,
David Schwab
forthcoming in Neural Computation (NECO)
arXiv /
code
We show how to use the (deterministic) information bottleneck to perform geometric clustering, introducing a novel informationtheoretic model selection criterion.


The deterministic information bottleneck
DJ Strouse,
David Schwab
Neural Computation (NECO), 2017 & Uncertainty in Artificial Intelligence (UAI), 2016
arXiv /
code /
UAI /
NECO
We introduce the deterministic information bottleneck (DIB), an alternative formulation of the information bottleneck that uses entropy instead of mutual information to measure compression. This results in a hard clustering algorithm with a builtin preference for using fewer clusters.


Using neural networks to understand the computational role of dendrites
DJ Strouse,
Balazs Ujfalussy,
Mate Lengyel
Computational and Systems Neuroscience (Cosyne), 2012
poster /
master's thesis /
why
We fit neural network models to single neuron data to understand the computational role of dendrites in integrating their synaptic input.


Optimizing online learning capacity in a biologicallyinspired neural network
Xundong Wu,
DJ Strouse,
Bartlett Mel
Society for Neuroscience (SfN), 2011
poster
We study the optimal conditions for online recognition memory in a biologicallyinspired neural network with "dendriteaware" learning rules.


Levinson's theorem for graphs
Andrew Childs,
DJ Strouse
Journal of Mathematical Physics (JMP), 2011
arXiv /
JMP /
talk
We prove an analog of a classic result in quantum scattering theory for the setting of scattering on graphs. The goal is to provide additional tools for designing quantum algorithms in this setting.

