Snapshots of ICML 2019

The 36th International Conference on Machine Learning (ICML) is by all accounts a premier conference in the machine learning world. Thousands of papers are submitted and thousands of people from around the world travel to attend the weeklong conference.

This year was no different with over 6,000 attendees and 2,473 submitted papers. Only 621 papers were accepted, along with 31 workshops and 11 tutorials.

Georgia Tech presented 19 papers and one workshop. The Machine Learning Center at Georgia Tech also hosted its first conference event for alumni, students, and faculty to gather. The center enjoyed hosting a lunch and seeing so many familiar faces all the way out in Long Beach, Calif.

While it’s humanly impossible to go to every talk during the week, we did our best.

If you were unable to make it out to Long Beach this year, we hope this helps with your FOMO. If you were fortunate enough to attend, let’s take a look back at this week together.

Let’s Set the Scene


Home sweet home for the week, the Long Beach Entertainment and Convention Center.
We’ve had worse views after a long day of machine learning talks.


The conference enjoys many large sponsors including Amazon, Facebook, Other sponsors include Tesla, Uber, Lyft, Bloomberg, Wayfair, Google, and more.
Each day ended with poster sessions by all of the authors who presented earlier in the day. This gives other attendees an opportunity to have in-depth discussions with the authors about their work.


The Conference


ML@GT Associate Director Le Song discusses his paper Generative Adversarial User Model for Reinforcement Learning Based Recommendation System during Tuesday night’s poster session.

Xinyan Yan and his co-author Ching-An Cheng discussed their research Predictor-Corrector Policy Optimization during Monday night’s poster session.
Ching-An Cheng gave a 20-minute oral presentation of Predictor-Corrector Policy Optimization to a packed house.
Students, alumni, and faculty gathered together on Wednesday for lunch at the King’s Fish House for the ML@GT ICML Luncheon.


Guests from across Georgia Tech’s campus enjoyed getting together for lunch and even brought home some fun ML@GT swag.

Tianyi Liu gets animated when discussing his research on Towards Understanding the Importance of Noise in Training Neural Networks during Wednesday night’s poster session.


Samira Samadi walks an attendee through her research on “Guarantees for Spectral Clustering with Fairness Constraints” during Thursday nights poster session.


Adrian Rivera Cardoso explains “Competing Against Equilibria in Zero-Sum Games with Evolving Payoffs” during the last poster session on Thursday evening. 

Karan Desai kept pace with the large crowd around his poster and helped explain various aspects of his work on “Probabilistic Neural-symbolic Models for Interpretable Visual Question Answering”.


Conferences provide a great opportunity to connect with new and old friends. Thinh T. Doan takes a moment to chat with some friends from MIT before walking a fellow attendee through his paper “Finite-Time Analysis of Distributed TD(0) with Linear Function Approximation on Multi-Agent Reinforcement Learning” 
Dan Tu gave an oral presentation to a packed room earlier in the day but breaks it down one-on-one later during the poster session.


This slideshow requires JavaScript.

For more information on Georgia Tech’s presence at ICML 2019, click here. For additional photos from the week, please visit our Flickr gallery. 

We’ll see you in Vienna at ICML 2020!

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s

This site uses Akismet to reduce spam. Learn how your comment data is processed.