The conference sold out in less than 12 minutes for its Dec. 2 - 8 gathering in Montreal, Quebec. As one of the biggest AI conferences in the world, tech companies like Google, Microsoft, and Facebook come to find new talent, while renowned researchers present their latest work.

A large number of Georgia Tech faculty and students will be among the throngs of attendees. With 26 papers by more than 23 Georgia Tech authors and several workshops to participate in, the Yellow Jackets are one of the leading contributors to the conference program.

Byron Boots and Dhruv Batra, assistant professors in the Machine Learning Center at Georgia Tech (ML@GT) and the School of Interactive Computing, are serving as area chairs.

“We are thrilled to be a top performing university at a conference of NeurIPS’ caliber. Our faculty and students continue to push boundaries and revolutionize our field, and it shows at events like this,” said Irfan Essa, ML@GT director.

As NeurIPS has increased in popularity since its first meeting in 1987, the conference receives thousands of submissions each year with a record high of 3,240 submissions in 2017. Over the years the content has shifted from examining biological and artificial neural networks and to focus more on AI, statistics, and machine learning.

Below is a list of Georgia Tech’s spotlight presentations, posters, and workshops being featured at NeurIPS next month.

Spotlights

• A Smoothed Analysis of the Greedy Algorithm for the Linear Contextual Bandit Problem

Sampath Kannan, Jamie Morgenstern, Aaron Roth, Bo Waggoner, and Steven Wu

• Learning Temporal Point Processes via Reinforcement Learning

Shuang Li, Shuai Xiao, Shixiang Zhu, Nan Du, Yao Xie, Le Song

• Robust Hypothesis Testing Using Wasserstein Uncertainty Sets

RUI GAO, Liyan Xie, Yao Xie, Huan Xu

• Limited Memory Kelley’s Method Converges for Composite Convex and Submodular Objectives

Song Zhou, Swati Gupta, and Madeleine Udell

• Learning Loop Invariants for Program Verification

Xujie Si, Hanjun Dai, Mukund Raghothaman, Mayur Naik, and Le Song

• Acceleration through Optimistic No-Regret Dynamics

Jun-Kun Wang and Jacob Abernethy

Posters

• Dual Policy Iteration

Wen Sun, Geoff Gordon, Byron Boots, and Drew Bagnell

• Differentiable MPC for End-to-End Planning and Control

Brandon Amos, Jake Sacks, Ivan Dario Jimenez, Byron Boots, and Zico Kolter

• Orthogonally Decoupled Variational Gaussian Processes

Hugh Samilbeni, Ching-An Cheng, Byron Boots, and Marc Deisenroth

• Learning and Inference in Hilbert Space with Quantum Graphical Models

Sid Srinivasan, Carlton Downey, and Byron Boots

• The Price of Fair PCA: One Extra Dimension

Samira Samadi, Uthaipon Tantipongpipat, Mohit Singh, Jamie Morgenstern, and Santosh Vempala

• A Smoothed Analysis of the Greedy Algorithm for the Linear Contextual Bandit Problem

Sampath Kannan, Jamie Morgenstern, Aaron Roth, Bo Waggoner, and Steven Wu

• Learning Temporal Point Processes via Reinforcement Learning

Shuang Li, Shuai Xiao, Shixiang Zhu, Nan Du, Yao Xie, Le Song

• Robust Hypothesis Testing Using Wasserstein Uncertainty Sets

RUI GAO, Liyan Xie, Yao Xie, Huan Xu

• Limited Memory Kelley’s Method Converges for Composite Convex and Submodular Objectives

Song Zhou, Swati Gupta, and Madeleine Udell

• Smoothed Analysis of Discrete Tensor Decomposition and Assemblies of Neurons

Nima Anari, Amin Saberi, Wolfgang Maass, Robert Legenstein, Christos Papadimitriou, and Santosh Vempala

• Differential Privacy for Growing Databases

Rachel Cummings, Sara Krehbiel, Kevin Lai, and Uthaipon (Tao) Tantipongpipat.

• Differentially Private Change-Point Detection

Rachel Cummings, Sara Krehbiel, Yajun Mei, Rui Tuo, and Wanrong Zhang

• Topkapi: Parallel and Fast Sketches for Finding Top-K Frequent Elements

Ankush Mandal, He Jiang, Anshumali Shrivastava, and Vivek Sarkar

• Overcoming Language Priors in Visual Question Answering with Adversarial Regularization

Sainandan Ramakrishnan, Aishwarya Agrawal, and Stefan Lee

• Partially Supervised Image Captioning

Peter Anderson, Stephen Gould, and Mark Johnson

• Learning towards Minimum Hyperspherical Energy

Weiyang Liu, Rongmei Lin, Zhen Liu, Lixin Liu, Zhiding Yu, Bo Dai, and Le Song

• Coupled Variational Bayes via Optimization Embedding

Bo Dai, Hanjun Dai, Niao He, Weiyang Liu, Zhen Liu, Jianshu Chen, Lin Xiao, and Le Song

• Learning Loop Invariants for Program Verification

Xujie Si, Hanjun Dai, Mukund Raghothaman, Mayur Naik, and Le Song

• Cooperative Neural Networks (CoNN): Exploiting Prior Independence Structure for Improved Classification

Harsh Shrivastava, Eugene Bart, Bob Price, Hanjun Dai, Bo Dai, Srinivas Aluru

• Dimensionality Reduction for Stationary Time Series via Stochastic Nonconvex Optimization

Minshuo Chen, Lin Yang, Mengdi Wang, and Tuo Zhao

• Towards Understanding Acceleration Tradeoff between Momentum and Asynchrony in Distributed Nonconvex Stochastic Optimization

Tianyi Liu, Shiyang Li, Jianping Shi, Enlu Zhou, and Tuo Zhao

• The Physical Systems behind Optimization Algorithms

Lin Yang, Raman Arora, Vladimir Braverman, and Tuo Zhao

• Provable Gaussian Embedding with One Observation

Ming Yu, Zhuoran Yang, Tuo Zhao, Mladen Kolar, and Zhaoran Wang

• Learning Towards Minimum Hyperspherical Energy

Weiyang Liu, Rongmei Lin, Zhen Liu, Lixin Liu, Zhiding Yu, Bo Dai, and Le Song

• Acceleration through Optimistic No-Regret Dynamics

Jun-Kun Wang and Jacob Abernethy

• MiME: Multilevel Medical Embedding of Electronic Health Records for Predictive Healthcare

Edward Choi, Cao Xiao, Walter F. Stewart, and Jimeng Sun

Workshops

• Workshop on AI in Finance

Tucker Balch, School of Interactive Computing Professor and Associate Chair, is an invited speaker.

• Visually-Grounded Interaction and Language (ViGIL)

Georgia Tech organizers include Erik Wijmans, Samyak Datta, Stefan Lee, Peter Anderson, Dhruv Batra, and Devi Parikh.

• Imitation Learning and its Challenges in Robotics

Interactive Computing Ph.D. student Mustafa Mukadam is organizing the workshop. 

• 2nd Black in AI Workshop

Application of The Hilbert Schmit Independence Criterion to Lexical Geographic Variation in Lyon, France by Taha Merghani 

• Wordplay: Reinforcement and Language Learning in Text-based Games

Playing Text-Adventure Games with Graph-Based Deep Reinforcement Learning 
Prithviraj Ammanabrolu and Mark O. Riedl