Title: Theoretical Foundations of Active Machine Learning Abstract: The field of Machine Learning (ML) has advanced considerably in recent years, but mostly in well-defined domains using huge amounts of human-labeled training data. Machines can recognize objects in images and translate text, but they must be trained with more images and text than a person can see in nearly a lifetime.  The computational complexity of training has been offset by recent technological advances, but the cost of training data is measured in…

Abstract: Studies of health behaviors using observational data are prone to bias from selection in behavior choices. How important are these biases? Are they dynamic - that is, are they influenced by the recommendations we make? Are there formal assumptions under which we can use information we have about selection on observed variables to learn about the possible bias from unobserved selection? About the Speaker: Emily Oster is a professor of economics. Prior to coming to Brown she was an…

Abstract: In many social science experiments, subjects often interact with each other and as a result, one unit's treatment can influence the outcome of another unit. Over the last decade, a significant progress has been made towards causal inference in the presence of such interference between units. In this talk, we will discuss two-stage randomized experiments, which enable the identification of the average spillover effects as well as that of the average direct effect of one's own treatment. In particular,…

Abstract: What if I told you I had evidence of a serious threat to American national security – a terrorist attack in which a jumbo jet will be hijacked and crashed every 12 days. Thousands will continue to die unless we act now. This is the question before us today – but the threat doesn’t come from terrorists. The threat comes from climate change and air pollution. We have developed an artificial neural network model that uses on-the-ground air-monitoring data…

Abstract: Representation learning seeks to represent complicated data (images, text etc.) using a vector embedding, which can then be used to solve complicated new classification tasks using simple methods like a linear classifier. Learning such embeddings is an important type of unsupervised learning (learning from unlabeled data) today. Several recent methods leverage pairs of "semantically similar" data points (eg sentences occuring next to each other in a text corpus). We call such methods contrastive learning (another term would be "like…

Abstract: Ranging from jury decisions to political elections, situations in which groups of individuals determine a collective outcome are ubiquitous. There are two important observations that pertain to almost all collective processes observed in reality. First, decisions are commonly preceded by some form of communication among individual decision makers, such as jury deliberations, or election polls. Second, even when looking at a particular context, say U.S. civil jurisdiction, there is great variance in the type of institutions that are employed…

Abstract: We construct a publicly available atlas of children’s outcomes in adulthood by Census tract using anonymized longitudinal data covering nearly the entire U.S. population. For each tract, we estimate children’s earnings distributions, incarceration rates, and other outcomes in adulthood by parental income, race, and gender. These estimates allow us to trace the roots of outcomes such as poverty and incarceration back to the neighborhoods in which children grew up. We find that children’s outcomes vary sharply across nearby areas: for children of parents at…

Abstract: The Regression Discontinuity (RD) design is one of the most widely used non-experimental strategies for the study of treatment effects in the social, behavioral, biomedical, and statistical sciences. In this design, units are assigned a score and a treatment is offered if the value of that score exceeds a known threshold---and withheld otherwise. In this talk, I will discuss the assumptions under which the RD design can be used to learn about treatment effects, and how to make valid…