.svg)
Transforming the Real World with AI: Petuum at NeurIPS 2019
In less than one week, the Petuum team will be heading to Vancouver, Canada, for the Thirty-third Conference on Neural Information Processing Systems (NeurIPS) to showcase how Petuum is transforming the real world with AI. NeurIPS 2019 will take place at the Vancouver Convention Center from December 8th to 14th, 2019. Each year, thousands of leading academics and researchers gather at NeurIPS to exchange research on neural information processing systems in biological, technological, mathematical and theoretical aspects.
As one of the world’s most prestigious machine learning conferences, NeurIPS had a record-breaking 6,743 submissions this year (more than double the 3,240 in 2016) which only 1,428 were accepted. Of the 21% of accepted papers, we are proud to announce that Petuum authors had five conference papers accepted. Additionally, we had five workshop papers accepted including, Mansi Gupta’s talk at the Women in Machine Learning Workshop that was selected as one of the 8 of ~600 submissions this year.
Along with our accepted conference and workshop papers (listed below), Petuum will be present at NeurIPS 2019 as a gold sponsor. We invite attendees to stop by our booth in the Exhibit Hall to see demos of our latest work, such as Petuum Neurobots, which provide cutting-edge AI capabilities in an easy-to-implement software solution. Neurobots AI/ML enhances traditional automation processes with sophisticated capabilities that include computer vision, context understanding, decision making, and more.
At Petuum, we’re working on real problems with our combined research and systems development in ML distributed systems and resource schedulers, general-purpose composable ML, time-series, natural language processing, computer vision, and real-time optimization. And we are looking forward to showing off our work next week in Vancouver. We are very proud of our researchers and their accomplishments that are helping artificial intelligence and machine learning grow. Through their hard work and dedication to the field, we are getting closer to our goal of making AI accessible to all companies in all industries.
Accepted Conference Papers
Offline Contextual Bayesian Optimization
Ian Char · Youngseog Chung · Willie Neiswanger · Kirthevasan Kandasamy · Oak Nelson · Mark Boyer · Egemen Kolemen · Jeff Schneider
Poster — Tuesday, December 10 5:30–7:30 PM @ East Exhibition Hall B + C #149
—
Specific and Shared Causal Relation Modeling and Mechanism-Based Clustering
Biwei Huang · Kun Zhang · Pengtao Xie · Mingming Gong · Eric Xing · Clark Glymour
Poster — Tuesday, December 10 5:30–7:30 PM @ East Exhibition Hall B + C #140
—
Learning Sample-Specific Models with Low-Rank Personalized Regression
Ben Lengerich · Bryon Aragam · Eric Xing
Poster — Wednesday, December 11 5:00–7:00 PM @ East Exhibition Hall B + C #43
—
Learning Data Manipulation for Augmentation and Weighting
Zhiting Hu · Bowen Tan · Russ Salakhutdinov · Tom Mitchell · Eric Xing
Poster — Thursday, December 12 10:45 AM — 12:45 PM @ East Exhibition Hall B + C #162
—
Learning Robust Global Representations by Penalizing Local Predictive Power
Haohan Wang · Songwei Ge · Zachary Lipton · Eric Xing
Poster — Thursday, December 12 10:45 AM — 12:45 PM @ East Exhibition Hall B + C #57
Accepted Workshop Papers
Adversarial Manipulation of Attention-based Explanations — Women in Machine Learning (WiML) Workshop
Mansi Gupta* · Danish Pruthi · Bhuwan Dhingra · Zachary Lipton · Graham Neubig
—
Deep Uncertainty Estimation for Model-based Neural Architecture Search — Bayesian Deep Learning Workshop
Colin White · Willie Neiswanger · Yash Savani
Poster Session — Friday, December 13 9:35–10:35 AM @ West Exhibition Hall C
—
Neural Architecture Search via Bayesian Optimization with a Neural Network Prior — Workshop on Meta-Learning (MetaLearn 2019)
Colin White · Willie Neiswanger · Yash Savani
Poster session — Friday, December 13 10:30–11:30 AM @ West Ballroom B
—
ChemBO: Bayesian Optimization of Small Organic Molecules with Synthesizable Recommendations — Machine Learning and the Physical Sciences Workshop
Ksenia Korovina · Sailun Xu · Kirthevasan Kandasamy · Willie Neiswanger · Barnabas Poczos · Jeff Schneider · Eric P. Xing
Poster session — Saturday, December 14 9:40–10:40 AM @ West 109 + 110
—
Offline Contextual Bayesian Optimization for Nuclear Fusion Tokamak Control — Machine Learning and the Physical Sciences Workshop
Youngseog Chung · Ian Char · Willie Neiswanger · Kirthevasan Kandasamy · Andrew Nelson · Mark Boyer · Egemen Kolemen · Jeff Schneider
Poster session — Saturday, December 14 9:40–10:40 AM @ West 109 + 110
—
If you are attending NeurIPS next week, please visit Petuum’s booth (#12) in the expo hall to meet with a few our dedicated researchers and learn how you can join them at Petuum to help enterprises solve real-world problems.
