Boosting With Multiple Sources
Dec 6, 2021
Speakers
Corinna Cortes
Speaker · 1 follower
Mehryar Mohri
Speaker · 4 followers
Dmitry Storcheus
Speaker · 0 followers
Ananda Theertha Suresh
Speaker · 0 followers
About
We study the problem of learning accurate ensemble predictors, in particular boosting, in the presence of multiple source domains. We show that the standard convex combination ensembles in general cannot succeed in this scenario and adopt instead a domain-weighted combination. We introduce and analyze a new boosting algorithm, , for this scenario and show that it benefits from favorable theoretical guarantees. We also report the results of several experiments with our algorithm demonstrating that it outperforms natural baselines on multi-source text-based, image-based and tabular data. Additionally, we present an extension of our algorithm to the federated learning scenario and report favorable experimental results for that setting as well.We study the problem of learning accurate ensemble predictors, in particular boosting, in the presence of multiple source domains. We show that the standard convex combination ensembles in general cannot succeed in this scenario and adopt instead a domain-weighted combination. We introduce and analyze a new boosting algorithm, , for this scenario and show that it benefits from favorable theoretical guarantees. We also report the results of several experiments with our algorithm demonstrating tha…
Organizer
NeurIPS 2021
Account · 1.9k followers
About NeurIPS 2021
Neural Information Processing Systems (NeurIPS) is a multi-track machine learning and computational neuroscience conference that includes invited talks, demonstrations, symposia and oral and poster presentations of refereed papers. Following the conference, there are workshops which provide a less formal setting.
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Optimizing with strange gradients
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
VAEs with Missing Data and Outliers
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Pl@ntNet-300K: a plant image dataset with high label ambiguity and a long-tailed distribution
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Towards a Theoretical Framework of Out-of-Distribution Generalization
Watch later
Haotian Ye, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Evaluating Bayes Error Estimators on Real-World Datasets with FeeBee
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
OmniPrint: A Configurable Printed Character Synthesizer
Watch later
Haozhe Sun, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%