Sign in
ICML 2020
Event Home
Maximum Likelihood With Bias-Corrected Calibration is Hard-To-Beat at Label Shift Adaptation
Jul 14, 2020
|
70 views
|
arXiv link
|
Code
Avanti Shrikumar
Follow
Domain Adaptation
149 videos · undefined sub area
Machine Learning
3863 videos · undefined sub area
Details
ICML 2020. Method that achieves state-of-the-art results at domain adaptation to label shift. Paper:
https://arxiv.org/abs/1901.06852
Authors: Amr Alexandari*, Anshul Kundaje†, Avanti Shrikumar*†. *co-first authors †co-corresponding authors
Category: ICML 2020
Comments
loading...
Reactions
(0)
| Note
📝 No reactions yet
Be the first one to share your thoughts!
Reactions
(0)
Note
loading...
Recommended
51:23
SREcon15 - From Zero to Hero: Recommended Practices for Training your Ever-Evolving SRE Teams
USENIX
| Apr 13, 2015
52:34
SREcon15 - Architecting and Launching the Halo 4 Services
USENIX
| Apr 13, 2015
43:05
SREcon15 - Being Afraid—How Paranoia at Dropbox Protects Your Data
USENIX
| Apr 13, 2015
20:58
ICAPS 2014: Jendrik Seipp on "Diverse and Additive Cartesian Abstraction Heuristics"
ICAPS
| Apr 14, 2015
20:15
ICAPS 2014: Bram Ridder on "Heuristic Evaluation Based on Lifted Relaxed Planning Graphs"
ICAPS
| Apr 14, 2015