-
NeurIPS 20192019Understanding the principles of causal inference in the visual system has a long history at least since the seminal studies by Albert Michotte. Many cognitive and machine learning scientists believe that intelligent behavior requires agents to possess causal models of the world. Recent ML algorithms exploit the dependence structure of additive noise terms for inferring causal structures from observational
-
NeurIPS 20192019Bayesian optimization (BO) is a successful methodology to optimize black-box functions that are expensive to evaluate. While traditional methods optimize each black-box function in isolation, there has been recent interest in speeding up BO by transferring knowledge across multiple related black-box functions. In this work, we introduce a method to automatically design the BO search space by relying on
-
CIKM 20192019In product search, users tend to browse results on multiple search result pages (SERPs) (e.g., for queries on clothing and shoes) before deciding which item to purchase. Users’ clicks can be considered as implicit feedback which indicates their preferences and used to re-rank subsequent SERPs...
-
NeurIPS 20192019Despite the recent progress in hyperparameter optimization (HPO), available benchmarks that resemble real-world scenarios usually consist of a few and very large problem instances that are expensive to solve. This blocks researchers and practitioners from systematically running large-scale comparisons that are needed to draw statistically significant results. This work proposes a method to alleviate these
-
NeurIPS 20192019Deep Neural Networks (DNNs) have yielded superior performance in many contemporary applications. However, the gradient computation in a deep model with millions of instances leads to a lengthy training process even with modern GPU/TPU hardware acceleration. In this paper, we propose AutoAssist, a simple framework to accelerate training of a deep neural network. Typically, as the training procedure evolves
Related content
-
May 05, 2021Kearns is a featured speaker at the first virtual Amazon Web Services Machine Learning Summit on June 2.
-
May 03, 2021Workshop at ICLR 2021 unites communities investigating synthetic data generation to improve machine learning and protect privacy.
-
April 30, 2021Amazon is collaborating with Caltech to support research, education, and outreach programs that help build bridges between AI and other areas of science and engineering.
-
April 29, 2021Amazon Scholar Aravind Srinivasan on the importance of machine learning for real-time and offline resource management.
-
April 28, 2021Yale economics professor Dirk Bergemann elected to American Academy of Arts & Sciences; University of Pennsylvania computer science professor Michael Kearns elected to National Academy of Sciences.
-
April 28, 2021Framework improves efficiency, accuracy of applications that search for a handful of solutions in a huge space of candidates.