DJ Strouse

I am a Research Scientist at DeepMind in London.

I did a PhD in Physics at Princeton University, advised by David Schwab and Bill Bialek, and funded by a Hertz Fellowship and a DOE Computational Science Graduate Fellowship. I did a master's at the University of Cambridge with Mate Lengyel as a 苹果手机怎么挂vnp教程 and studied physics and mathematics at the University of Southern California, where I worked with Bartlett Mel and Paolo Zanardi and had a blog. Throughout my studies, I also spent time at DeepMind working with Matt Botvinick, Stanford University working with 国内ipad怎么看youtube, the Institute for Quantum Computing working with Andrew Childs, and Spotify NYC working with their machine learning team.

Email  /  Twitter  /  CV  /  Scholar  /  翻外墙看youtube加速软件

I'm interested in reinforcement learning (RL), information theory, and deep learning with an eye toward understanding and creating intelligent agents. My PhD thesis ("Optimization of MILES") focussed on applications of the information bottleneck (IB) in supervised, unsupervised, and reinforcement learning. In the past, I've also worked on quantum information theory and computational neuroscience.

We present a deep learning approach to auction design that guarantees truthfulness (bidders are incentivized to be honest) and efficiency (whoever wants the item most gets it). We focus on social utility maximizing auctions, where the goal is to achieve the former constraints while placing as little economic burden on the bidders as possible.

We reward agents for influencing the actions of other agents, and show that this gives rise to better cooperation and more meaningful emergent communication protocols.

YouTube(油管)的安装、使用、视频下载和国内访问 - 玩个机吧:2021-11-29 · YouTube（油管）作为全球最大的视频网站，拥有来自世界各国的视频资源。今天，我伔聊聊关于油管的画质、安装、字幕自动生成和视频下载。 8K 画质 与油管支持 8K 60帧 相比，国内各视频网站最高是 1080P， …

We train agents in multi-goal environments with an information bottleneck between their goal and policy. This encourages agents to develop useful "habits" that generalize across goals. We identify the states where agents must deviate from their habits to solve a task as "decision states" and show that they are useful targets for an exploration bonus.

We train agents to cooperate / compete by regularizing the reward-relevant information they share with other agents, enabling agents trained alone to nevertheless perform well in a multi-agent setting.

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 built-in preference for using fewer clusters.

We describe how to use the variational 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.

We study the optimal conditions for online recognition memory in a biologically-inspired neural network with "dendrite-aware" learning rules.

We fit neural network models to single neuron data to understand the computational role of dendrites in integrating their synaptic input.

Apple Store被抢 库克要捐款 Google、微软也发声 - the ...:2021-6-2 · 当一场大火熊熊燃烧的时候，没有人知道它的边界在哪里。对于当下的美国来说，这场大火就是由美国非裔男子GeorgeFloyd之死引发的全国性游行抗议 ...

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.

Good artists copy.