July 18th - July 24th

ICML 2021

View information on Facebook AI’s published papers and presentations at the upcoming 38th edition of the International Conference on Machine Learning (ICML)

Our Work

Outstanding Paper Award

June 30, 2021

Core Machine Learning

Understanding Self-Supervised Learning Dynamics without Contrastive Pairs

Yuandong Tian, Xinlei Chen, Surya Ganguli

June 30, 2021

Read the Paper

Featured Publications

Few-Shot Neural Architecture Search

Efficient evaluation of a network architecture drawn from a large search space remains a key challenge in Neural Architecture Search (NAS) …

Learn-to-Share: A Hardware-friendly Transfer Learning Framework Exploiting Computation and Parameter Sharing

Task-specific fine-tuning on pre-trained transformers has achieved performance breakthroughs in multiple NLP tasks. Yet, as both computation and parameter size grows linearly with the number …

AlphaNet: Improved Training of Supernets with Alpha-Divergence

Weight-sharing neural architecture search (NAS) is an effective technique for automating efficient neural architecture design. …

Improving Lossless Compression Rates via Monte Carlo Bits-Back Coding

Latent variable models have been successfully applied in lossless compression with the bits-back coding algorithm. However, bits-back suffers from an increase in the bit rate equal to

Understanding self-supervised learning dynamics without contrastive pairs

While contrastive approaches of self-supervised learning (SSL) learn representations by minimizing the distance between two augmented views of the same data point …

See All Papers

Event Highlights

Latinx in AI Workshop

July 19, 2021 8:00 am - 7:00 PM (PDT)

Cristian Canton is a speaker.

Women in Machine Learning Un-Workshop

July 21, 2021, 6:40 am - 8:45am (PDT)

Join speaker Amy Zhang and Facebook AI recruiters.

Workshops

ICML 2021 Workshop on Unsupervised Reinforcement Learning

Fri Jul 23 05:45 AM -- 02:30 PM (PDT)
Feryal Behbahani, Joelle Pineau, Lerrel Pinto, Roberta Raileanu, Aravind Srinivas, Denis Yarats, Amy Zhang

Self-Supervised Learning for Reasoning and Perception

Sat Jul 24 08:00 AM -- 06:50 PM (PDT)
Pengtao Xie, Shanghang Zhang, Ishan Misra, Pulkit Agrawal, Katerina Fragkiadaki, Ruisi Zhang, Tassilo Klein, Asli Celikyilmaz, Mihaela van der Schaar, Eric Xing

ICML Workshop on Human in the Loop Learning (HILL)

Sat Jul 24 04:15 AM -- 11:10 AM (PDT)
Trevor Darrell, Xin Wang, Been Kim, Li Erran Li, Fisher Yu, Zeynep Akata, wenwu zhu, Pradeep Ravikumar, Shiji Zhou, Shanghang Zhang, Kalesha Bullard

Information-Theoretic Methods for Rigorous, Responsible, and Reliable Machine Learning (ITR3)

Sat Jul 24 07:00 AM -- 07:00 PM (PDT)
Ahmad Beirami, Flavio Calmon, Berivan Isik, Haewon Jeong, Matthew Nokleby, Cynthia Rush

Workshop on Reinforcement Learning Theory

Sat Jul 24 09:00 AM -- 04:25 PM (PDT)
Shipra Agrawal,Simon Du, Niao He, Csaba Szepesvari, Lin Yang

View All ICML Workshops

What is Pytorch?

Pytorch is an open source machine learning framework that accelerates the path from research prototyping to production deployment.

See Video

Learn More

Help Us Pioneer the Future of AI

We share our open source frameworks, tools, libraries, and models for everything from research exploration to large-scale production deployment.

Product experiences