Petuum Blog

Latest blog

Pushing the Vanguard of Natural Language Generation (NLG) using Language Models as Discriminators

“For last year's words belong to last year's language And next year's words await another voice.” ― T.S. Eliot, Four Quartets

Intro to Modern Bayesian Learning and Probabilistic Programming

What is Bayesian machine learning? To answer this question, it is helpful to first take a look at what happens in typical machine learning procedures (even non-Bayesian ones). In nearly all cases,...

Are you ready for NeurIPS 2018?

We mentioned in a previous post how excited we are that eight papers by Petuum authors were accepted to NeurIPS 2018, the 32nd Conference on Neural Information Processing Systems. They’ll be...

Connecting the Dots Between MLE and RL for Sequence Generation

Crossposted on the Texar blog. Sequence generation is a ubiquitous problem in many applications, such as machine translation, text summarization, image captioning, and so forth. Recently, we...

Introduction to Interpretable Machine Learning

By Seojin Bang We have witnessed the rise of sophisticated, autonomous task-performing systems such as self-driving cars, product recommendations, language translators, and targeted...

Petuum’s Pengtao Xie Named a Pittsburgh 2018 Innovator — Congratulations, Pengtao!

Our Senior Director of Data Solutions and Service, Pengtao Xie, has been selected as a winner of the Pittsburgh Business Times’ Innovator Awards 2018! We are proud to share the news and...

Petuum at the WEF Annual Meeting of New Champions

By Eric Xing, CEO, Founder, and Chief Scientist at Petuum It was an honor to represent Petuum, a 2018 Technology Pioneer, at the World Economic Forum’s Annual Meeting of the New Champions in...

8 Petuum Papers Accepted to NeurIPS 2018

We are happy to share the news that eight papers with Petuum authors have been accepted to NeurIPS 2018, the 32nd Conference on Neural Information Processing Systems, and will be presented at...

Introducing Texar: A Modularized, Versatile, and Extensible Toolkit for Text Generation and Beyond

Crossposted on the Texar blog. We are excited to introduce Texar, an open-source, general-purpose toolkit that supports a broad set of machine learning applications with a focus on text...