Completed
Proposed Solution: Data Aggregation with Transfer Learning
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Data Efficiency Through Transfer Learning - Eddie Du
Automatically move to the next video in the Classroom when playback concludes
- 1 Intro
- 2 About Georgian Partners
- 3 Proposed Solution: Data Aggregation with Transfer Learning
- 4 Instance-based Transfer Learning
- 5 Mathematical Justification
- 6 Bluecore's Challenge: Binary classification while preserving privacy
- 7 Proposed Solution: Aggregate at the Model level
- 8 What does it mean to preserve privacy?
- 9 First attempt at preserving privacy
- 10 Revisiting the Compensation Example
- 11 Quantifying Privacy with Differential Privacy
- 12 Differential Privacy in Machine Learning
- 13 Using Differential Privacy in Practice
- 14 Recall the Proposed Solution for Bluecore
- 15 Differentially Private Logistic Regression
- 16 Effect of Epsilon on Performance
- 17 Summary
