Latest news
View All-
July 02, 2020Seeger and three coauthors are honored for paper that forged durable links between previously separate domains.
-
July 02, 2020Method automatically generates negative training examples for deep-learning model.
-
July 02, 2020Amazon researchers coauthor 17 conference papers, participate in seven workshops.
-
-
July 5 - 8, 2020
-
July 5 - 10, 2020
-
-
June 29, 2020Alexa AI vice president of natural understanding Prem Natarajan discusses the upcoming NSF cycle for collaboration on fairness in AI, and other topics.
-
June 24, 2020Amazon scientists are on the cutting edge of using math-based logic to provide better network security, access management, and greater reliability.
-
June 24, 2020System enables efficient updating and parallelization and stable scaling.
-
June 18, 2020From counting fish to identifying touchdowns, AWS customers are utilizing computer vision and pattern recognition technologies to improve business processes and customer experiences.
Recent publications
View All-
2020
We consider recovering a causal graph in presence of latent variables, where we seek to minimize the cost of interventions used in the recovery process. We consider two intervention cost models: (1) a linear cost model where the cost of an intervention on a subset of variables has a linear form, and (2) an identity cost model where the cost of an intervention is the same, regardless of what variables it -
2020
We introduce a new way of learning to encode position information for non-recurrent models, such as Transformer models. Unlike RNN and LSTM, which contain inductive bias by loading the input tokens sequentially, non-recurrent models are less sensitive to position. The main reason is that position information among input units is not inherently encoded, i.e., the models are permutation equivalent; this problem -
2020
Extreme multi-label classification (XMC) is the problem of finding the relevant labels for an input, from a very large universe of possible labels. We consider XMC in the setting where labels are available only for groups of samples - but not for individual ones. Current XMC approaches are not built for such multi-instance multi-label (MIML) training data, and MIML approaches do not scale to XMC sizes. -
ICML AutoML Workshop 20202020
Bayesian optimization (BO) is a class of global optimization algorithms ubiquitous in hyperparameter optimization (HPO). BO budgets are typically given in iterations, which implicitly measures convergence in terms of the number of hyperparameter evaluations. In practice, evaluation costs may vary in different regions of the search space. For example, the cost of neural network training increases quadratically -
ICML AutoML Workshop 20202020
Given the increasing importance of machine learning in our lives and the need for algorithmic fairness, several methods have been proposed to measure and mitigate biases in machine learning models. Commonly, these techniques are specialized approaches applied to a single type of model and a specific definition of fairness, limiting their effectiveness in practice. In this paper, we present a general constrained
Research areas
Working at Amazon
Learn More-
June 23, 2020Scientists from glamazon, Amazon’s LGBTQIA+ affinity group, say this year's Pride Month is as much about solidarity as it is about celebration.
Work with us
See More JobsAcademic engagements
Learn More-
June 17, 2020Recipients represent 39 universities in 10 countries.
-
May 04, 2020Award-winning scientist joined Amazon team in Tübingen earlier this year.
Videos and webinars
View All-
June 19, 2020Watch the fireside chat featuring Charlie Bell, senior vice president of Amazon Web Services.
-
June 10, 2020Watch the webcast discussion with Gerard Medioni, Amazon distinguished scientist, Pietro Perona, Amazon Fellow, and Larry Davis, Amazon senior principal scientist.
Resources
-
Discover more customer-obsessed science and innovation from around Amazon, including the AWS News Blog and the official Amazon Blog: Day One.
-
Check out the latest news and innovations from Amazon’s scientific community, which have been featured in the media around the world.

