-
2024Graph machine learning (GML) is effective in many business applications. However, making GML easy to use and applicable to industry applications with massive datasets remain challenging. We developed GraphStorm, which provides an end-to-end solution for scalable graph construction, graph model training and inference. GraphStorm has the following desirable properties: (a) Easy to use: it can perform graph
-
2024We focus on the task of learning the value function in the reinforcement learning (RL) setting. This task is often solved by updating a pair of online and target networks while ensuring that the parameters of these two networks are equivalent. We propose Lookahead-Replicate (LR), a new value-function approximation algorithm that is agnostic to this parameter-space equivalence. Instead, the LR algorithm
-
2024Existing work in scientific machine learning (SciML) has shown that data-driven learning of solution operators can provide a fast approximate alternative to classical numerical partial differential equation (PDE) solvers. Of these, Neural Operators (NOs) have emerged as particularly promising. We observe that several uncertainty quantification (UQ) methods for NOs fail for test inputs that are even moderately
-
Transactions on Machine Learning Research2024Recent breakthroughs in large language modeling have facilitated rigorous exploration of their application in diverse tasks related to tabular data modeling, such as prediction, tabular data synthesis, question answering, and table understanding. Each task presents unique challenges and opportunities. However, there is currently a lack of comprehensive review that summarizes and compares the key techniques
-
FORC 20242024We study the problem of collecting a cohort or set that is balanced with respect to sensitive groups when group membership is unavailable or prohibited from use at deployment time. Specifically, our deployment-time collection mechanism does not reveal significantly more about the group membership of any individual sample than can be ascertained from base rates alone. To do this, we study a learner that
Related content
-
April 28, 2021Framework improves efficiency, accuracy of applications that search for a handful of solutions in a huge space of candidates.
-
April 23, 2021To mark the occasion, Amazon Science showcases some of the top-selling artificial-intelligence books, and passages from each book that Kindle customers have highlighted most frequently.
-
April 22, 2021The Middle Mile team manages complexity and scale in making routing decisions across the company’s expansive transportation network.
-
April 21, 2021Polito is one of the featured speakers at the first virtual Amazon Web Services Machine Learning Summit on June 2.
-
April 08, 2021Virtual event on June 2 will include science track.
-
April 06, 2021Ability to balance parameter size and effectiveness could be “extremely useful” in reducing parameter size of deep-learning models.