Joint ML Journal Club 15
O1.435 (FTX seminar room)
Building 1d
Do you want to get the very latest news on research in ML?
The joint journal club meets on the second Friday of each month, covering new ML research for physicists across the board. We are a diverse group from theory to experiment, high energy to astrophysics. Everyone is welcome.
In this meeting, we will read about Data Shapley; https://arxiv.org/abs/2406.11011
Data Shapley is a way of assigning each data point a score that indicates how much it contributes to the performance of your model. For calculating this, previous approaches relied on doing multiple training runs on different data subsets. This paper presents a method for an efficient calculation during training with small additional runtime.
If you need a map, one is found here; https://indico.desy.de/event/45937/#preview:124922
Join Zoom Meeting: https://desy.zoom.us/j/69478568183
Meeting ID: 694 7856 8183
Passcode: MLclub
Mailing list: jointml@desy.de. We will announce upcoming meetings there. To subscribe, please visit lists.desy.de/sympa/subscribe/jointml.
Please do suggest papers (or tools, or anything else) that interest you! Or perhaps you'd like to present one of our suggested papers; github.com/HenryDayHall/JointML