Sally Goldman
Sally joined Google Research in 2008. She holds a PhD from MIT, where she worked under the supervision of Ron Rivest. After completing her dissertation in computational learning theory, Sally was a professor and Associate Chair at Washington University in St. Louis. At Google, she focuses on recommender systems, conversational recommenders, and UX research related to recommenders. Sally has also dedicated time to teaching machine learning to underrepresented groups as an academic lead for Tech Exchange and Curriculum Committee and AI Studio lead for Breakthrough Tech AI.
Authored Publications
Sort By
Data Bootstrapping for Interactive Recommender Systems
Ajay Joshi
Ajit Apte
Anand Kesari
Anushya Subbiah
Dima Kuzmin
John Anderson
Li Zhang
Marty Zinkevich
The 2nd International Workshop on Online and Adaptive Recommender Systems (2022)
Preview abstract
Modifying recommender systems for new kinds of user interactions is costly and exploration is slow since machine learning models can be trained and evaluated on live data only after a product supporting these new interactions is deployed. Our data bootstrapping approach moves the task of developing models for new interactions into the input representation allowing a standard machine learning model (e.g. a transformer model) to be used to train a model capturing the new interactions. More specifically, we use data obtained from a launched system to generate simulated data that includes the new interactions options. This approach helps accelerate model and algorithm development, and reduce the time to launch new interaction experiences. We present machine learning methods designed specifically to work well with limited and noisy data produced via data bootstrapping.
View details
Google Tech Exchange: An Industry-Academic Partnership That Prepares Black and Latinx Undergraduates for High-Tech Careers
Alycia Onowho
Ann Gates
April Alvarez
Bianca Francesca Okafor
Gloria Washingon
Harry Keeling
Jean M Griffin
Legand Burge
Mary Jo Madda
Shameeka Scott Emanuel
Consortium for Computing Sciences in Colleges - Southwest (2020), pp. 6-8
Preview abstract
This paper describes Google Tech Exchange, an industry-academic partnership that involves several Historically Black Colleges and HispanicServing Institutions.Tech Exchange’s mission is to unlock opportunities in the tech industry for Black and Latinx undergraduates. It is an immersive computer science experience for students and faculty. Participants spend a semester or two at Google in Silicon Valley taking or co-teaching computer science courses, including cutting-edge ones not offered at many universities. The 2018-2019 graduates especially valued the community-building, and a high percentage secured technical internships or jobs.
View details
Preview abstract
TAPAS is a novel adaptive sampling method for the softmax model. It uses a two pass sampling strategy where the examples used to approximate the gradient of the partition function are first sampled according to a squashed population distribution and then resampled adaptively using the context and current model. We describe an efficient distributed implementation of TAPAS. We show, on both synthetic data and a large real dataset, that TAPAS has low computational overhead and works well for minimizing the rank loss for multi-class classification problems with a very large label space.
View details
