I am Dhaval Adjodah, a machine learning and policy
researcher working on pushing the limits of modern machine learning while maximizing their social good.
Currently, I am a research scientist at the MIT Quest for Intelligence whose purpose is to make advances towards building machine intelligence. I do impact-focused work with local communities at the Center of Complex Interventions and I am also a consultant for the World Bank, where I am helping build new machine learning pipelines to track and implement SDG policy. Previously, I was a research scientist at the MIT Media Lab where I developed new machine learning algorithms using insights from computational social science.
My PhD thesis was in computational social science and reinforcement learning. I also was a member of the Harvard Berkman Assembly on Ethics and Governance in Artificial Intelligence, and was a fellow at the Dalai Lama Center For Ethics And Transformative Values. Previously, I worked as a data scientist in banking and insurance, consulted with the Veterans Health Administration, and founded two startup incubators. I hold a masters degree from the Technology and Policy Program from the (now) Institute for Data, Systems and Society, and a bachelors in Physics, also from MIT.
In addition to my day-to-day work (machine learning engineering, running live online human experiments and writing papers), I enjoy being of service to the computer science and social science communities, most recently as a member of the organizing committee of the AI for Social Good conference workshop series, and on the program committees of the Black in AI initiative and Theoretical Foundations of Reinforcement Learning workshop.
My email is contact dot dval dot me at gmail dot com. I'm also on Twitter. Github here. I do not check LinkedIn often.
Mask mandates, adherence, and attitudes on COVID-19
We investigate an unprecedented breadth and depth of health outcomes, geographical resolutions, types of mask mandates, early versus later waves and controlling for other government interventions, mobility testing rate and weather. We show that mask mandates are associated with a statistically significant decrease in new cases (-3.55 per 100K), deaths (-0.13 per 100K), and the proportion of hospital admissions (-2.38 percentage points) up to 40 days after the introduction of mask mandates both at the state and county level. These effects are large, corresponding to 14% of the highest recorded number of cases, 13% of deaths, and 7% of admission proportion. We also introduce the novel results that community mask adherence and community attitudes towards masks are associated with a reduction in COVID-19 cases and deaths.
[Code, Working Paper]
Bayesian Models of Cognition in the Wisdom of the Crowd
How do we design and deploy crowdsourced prediction platforms for real-world applications where risk is an important dimension of prediction performance? To help answer this question, we conducted a large online Wisdom of the Crowd study where participants predicted the prices of real financial assets (e.g. S&P 500). We observe a Pareto frontier between accuracy of prediction and risk, and find that this trade-off is mediated by social learning i.e. as social learning is increasingly leveraged, it leads to lower accuracy but also lower risk. We also observe that social learning leads to superior accuracy during one of our rounds that occurred during the high market uncertainty of the Brexit vote. Our results have implications for the design of crowdsourced prediction platforms: for example, they suggest that the performance of the crowd should be more comprehensively characterized by using both accuracy and risk (as is standard in financial and statistical forecasting), in contrast to prior work where risk of prediction has been overlooked.
Leveraging Communication Topologies Between Deep RL Agents
There has been a lot of recent work showing that sparsity in neural network structure can lead to huge improvements, such as through the Lottery Ticket Hypothesis. Coming from a computational social science background, we know that humans self-organize into sparse social networks. My hypothesis was that organizing the communication topology (social network) between agents might lead to improvements in learning performance. This is especially important because some machine learning paradigms—especially reinforcement learning—are becoming more and more distributed in order to parallelize learning, similar to how human society balances exploration and exploitation. Well, we find huge improvements: 10–798% improvement on the state-of-the-art robotics simulators! Accepted at AAMAS 2020. [Code, Paper]