Tamara Broderick

About

Tamara Broderick is an Associate Professor of Electrical Engineering and Computer Science (EECS) at MIT. Her research focuses on artificial intelligence and machine learning, particularly in developing techniques for the analysis and synthesis of systems that interact with the external world through perception, communication, and action. Her work involves systems that learn, make decisions, and adapt to changing environments, contributing to the advancement of AI methodologies and their applications. As part of her academic role, she engages in research that leverages computational, theoretical, and experimental tools to address shared human challenges through innovative AI solutions. Her expertise and contributions are integral to the department's efforts in exploring all research areas related to AI and decision-making, fostering advancements in intelligent systems and their societal impacts.

Research topics

• Computer science
• Mathematics
• Algorithm
• Artificial intelligence
• Applied mathematics

Selected publications

• Diffusion probabilistic modeling of protein backbones in 3D for the motif-scaffolding problem

  arXiv (Cornell University) · 2022-06-08 · 96 citations

  preprintOpen access

  Construction of a scaffold structure that supports a desired motif, conferring protein function, shows promise for the design of vaccines and enzymes. But a general solution to this motif-scaffolding problem remains open. Current machine-learning techniques for scaffold design are either limited to unrealistically small scaffolds (up to length 20) or struggle to produce multiple diverse scaffolds. We propose to learn a distribution over diverse and longer protein backbone structures via an E(3)-…

  PublisherOA PDFDOI

• An Automatic Finite-Sample Robustness Metric: When Can Dropping a Little\n Data Make a Big Difference?

  arXiv (Cornell University) · 2020-11-30 · 15 citations

  preprintOpen access1st author

  Study samples often differ from the target populations of inference and\npolicy decisions in non-random ways. Researchers typically believe that such\ndepartures from random sampling -- due to changes in the population over time\nand space, or difficulties in sampling truly randomly -- are small, and their\ncorresponding impact on the inference should be small as well. We might\ntherefore be concerned if the conclusions of our studies are excessively\nsensitive to a very small proportion of our…

  PublisherOA PDFDOI

• Validated Variational Inference via Practical Posterior Error Bounds

  OpenBU (Boston University) · 2020-06-03 · 11 citations

  articleOpen accessSenior author

  Variational inference has become an increasingly attractive fast alternative to Markov chain Monte Carlo methods for approximate Bayesian inference. However, a major obstacle to the widespread use of variational methods is the lack of post-hoc accuracy measures that are both theoretically justified and computationally efficient. In this paper, we provide rigorous bounds on the error of posterior mean and uncertainty estimates that arise from full-distribution approximations, as in variational in…

  PublisherOA PDF

• A Usability Study of Nomon: A Flexible Interface for Single-Switch Users

  2023-10-19 · 3 citations

  articleOpen accessSenior author

  Many individuals with severe motor impairments communicate via a single switch—which might be activated by a blink, facial movement, or puff of air. These switches are commonly used as input to scanning systems that allow selection from a 2D grid of options. Nomon is an alternative interface that provides a more flexible layout, not confined to a grid. Previous work suggests that, even when options appear in a grid, Nomon may be faster and easier to use than scanning systems. However, previous w…

  PublisherOA PDFDOI

• Multi-marginal Schrödinger Bridges with Iterative Reference Refinement

  arXiv (Cornell University) · 2024-08-12 · 1 citations

  preprintOpen accessSenior author

  Practitioners often aim to infer an unobserved population trajectory using sample snapshots at multiple time points. E.g., given single-cell sequencing data, scientists would like to learn how gene expression changes over a cell's life cycle. But sequencing any cell destroys that cell. So we can access data for any particular cell only at a single time point, but we have data across many cells. The deep learning community has recently explored using Schrödinger bridges (SBs) and their extensions…

  PublisherOA PDFDOI

Recent grants

• CAREER: Robust, scalable, reliable machine learning

  NSF · $550k · 2018–2024

Frequent coauthors

• Michael I. Jordan

  51 shared

• Ryan Giordano

  36 shared

• Trevor Campbell

  34 shared

• Jonathan H. Huggins

  Dow Chemical (United States)

  30 shared

• William Stephenson

  Genomic Health (United States)

  16 shared

• Brian L. Trippe

  15 shared

• Raj Agrawal

  12 shared

• Tin D. Nguyen

  12 shared

Labs

• MIT EECS Artificial Intelligence + Decision-making LabPI

Awards & honors

• Eleven MIT faculty receive Presidential Early Career Awards

Similar researchers at Massachusetts Institute of Technology

• Manolis Kellish-164
• Antonio Torralbah-133
• Daniela Rush-129