Overview
The International Conference on Machine Learning (ICML) is the premier gathering of professionals dedicated to the advancement of the branch of artificial intelligence known as machine learning. The conference is globally renowned for presenting and publishing cutting-edge research on all aspects of machine learning used in closely related areas like artificial intelligence, statistics and data science, as well as important application areas such as machine vision, computational biology, speech recognition, and robotics.
Accepted publications
-
ICML 2022, UAI 2022 Workshop on Advances in Causal Inference2022
Workshops
ICML 2022 Workshop on Safe Learning for Autonomous Driving
July 22
This workshop will bring together researchers and industry practitioners from different AI subfields to work towards safer and more robust autonomous technology.
Amazon organizer: Erran Li
Amazon speakers: Todd Hester, Kumar Chellapilla
Website: https://learn-to-race.org/workshop-sl4ad-icml2022
Amazon organizer: Erran Li
Amazon speakers: Todd Hester, Kumar Chellapilla
Website: https://learn-to-race.org/workshop-sl4ad-icml2022
ICML 2022 Workshop on Updatable Machine Learning
July 23
This workshop will bring together researchers from various ML communities to discuss recent theoretical and empirical developments in updatable machine learning
Amazon speakers: Aaron Roth (Amazon Scholar)
Website: https://upml2022.github.io
Amazon speakers: Aaron Roth (Amazon Scholar)
Website: https://upml2022.github.io
ICML 2022 Workshop on Pre-training: Perspectives, Pitfalls, and Paths Forward
July 22
ICML 2022 Workshop on the Theory and Practice of Differential Privacy
July 22
Related content
Learn more about Amazon's presence at ICML.
-
July 27, 2023Determining on the fly how much additional audio to process to resolve ambiguities increases accuracy while reducing latency relative to fixed-lookahead approaches.
-
July 21, 2023Across a range of topics, Amazon research blends the theoretical and the practical.
-
July 22, 2022Combining a cutting-edge causal-inference technique and end-to-end machine learning reduces root-mean-square error by 27% to 38%.