-
SIGIR 20232023Uncertainty quantification is one of the most crucial tasks to obtain trustworthy and reliable machine learning models for decision making. However, most research in this domain has only focused on problems with small label spaces and ignored eXtreme Multilabel Classification (XMC), which is an essential task in the era of big data for web-scale machine learning applications. Moreover, enormous label spaces
-
CLeaR 20232023This paper demonstrates how to discover the whole causal graph from the second derivative of the log-likelihood in observational nonlinear additive Gaussian noise models. Leveraging scalable machine learning approaches to approximate the score function ∇ log p(X), we extend the work of Rolland et al. (2022) that only recovers the topological order from the score and requires an expensive pruning step removing
-
CLeaR 20232023Learning generative object models from unlabelled videos is a long standing problem relevant for causal scene modeling. We decompose this task into three easier subtasks, and provide candidate solutions for each of them. Inspired by the Common Fate Principle of Gestalt Psychology, we first extract (noisy) masks of moving objects via unsupervised motion segmentation. Second, generative models are trained
-
2023We advance the study of incentivized bandit exploration, in which arm choices are viewed as recommendations and are required to be Bayesian incentive compatible. Recent work of (Sellke & Slivkins, 2022) has shown that for the special case of independent arms, after collect-ing enough initial samples, the popular Thomp-son sampling algorithm becomes incentive com-patible. This was generalized to the combinato-rial
-
ICME 20232023Keyword Spotting (KWS) is a critical aspect of audio-based applications on mobile devices and virtual assistants. Recent developments in Federated Learning (FL) have significantly expanded the ability to train machine learning models by utilizing the computational and private data resources of numerous distributed devices. However, existing FL methods typically require that devices possess accurate ground-truth
Related content
-
December 14, 2022Alexa Fund company’s assisted reality tech could unlock speech for hundreds of millions of people who struggle to communicate.
-
December 12, 2022Vice president of ML and AI Services says more than 100,000 customers are doing machine learning on AWS.
-
December 12, 2022Vice president Bratin Saha reflects on the past and future of Amazon Web Services’ machine learning tools and AI services.
-
December 07, 2022Learn about a real-time continual, lifelong learning system that trains machine learning models using production data at scale.
-
December 05, 2022Internal event designed to replicate external science conferences.
-
December 05, 2022Accounting for data heterogeneity across edge devices enables more useful model updates, both locally and globally.
-
December 02, 2022Learn about the development, operational, and process improvements that can be incorporated by organizations to improve the explainability of models while adhering to regulatory requirements.
-
December 02, 2022Faculty projects are focused on various aspects of trustworthy machine learning.
-
December 01, 2022At re:Invent, AWS announces that the CodeWhisperer preview has added support for two new programming languages.
-
November 30, 2022When optimizing for a new solution in deep reinforcement learning, it helps if the optimizer gravitates toward the previous solution.
-
November 30, 2022Prem Natarajan, Alexa AI vice president, and Michael Kearns, an Amazon Scholar, discuss fairness, accountability, transparency, and ethics topics applied to machine learning, automation, robotics, and space themes.
-
November 29, 2022Using the prior model to rerank outputs of the new model increases backward compatibility.
-
November 23, 2022Three questions with Sergül Aydöre, a senior applied scientist at Amazon and general chair of this year’s Women in Machine Learning workshop.
-
November 22, 2022Francesco Locatello on the four NeurIPS papers he coauthored this year, which largely concern generalization to out-of-distribution test data.
-
November 21, 2022Topics range from specific applications, such as computer vision, to more general problems, such as continual learning, to popular AI methods, such as variational autoencoders.
-
November 18, 2022Targeted handling of three distinct types of “special events” dramatically reduces false-alarm rate.
-
November 15, 2022Teaching robots to stow items presents a challenge so large it was previously considered impossible — until now.
-
November 10, 2022New approach can cut the setup time required to develop vision-based machine learning solutions from between six to twelve months to one or two.
-
November 09, 2022At Amazon, he develops machine learning models to help keeping Amazon stores safe and trustworthy for customers and selling partners.
-
November 08, 2022Eliminating the need for annotation makes bias testing much more practical.
-
November 03, 2022Tim Kraska, who joined Amazon this summer to build the new Learned Systems research group, explains the power of “instance optimization”.