Completed
Intro
Class Central Classrooms beta
YouTube playlists curated by Class Central.
Classroom Contents
Learning Representations Using Causal Invariance - Leon Bottou
Automatically move to the next video in the Classroom when playback concludes
- 1 Intro
- 2 Joint work with
- 3 Summary
- 4 Why machine learning?
- 5 The statistical problem is only a proxy Example: detection of the action giving a phone call
- 6 A conjecture about adversarial features
- 7 Spurious correlations
- 8 Past observations
- 9 Nature does not shuffle the data. We do!
- 10 Multiple environments
- 11 Negative mixtures matter! Consider a search engine query classification problem
- 12 Learning stable properties
- 13 Invariance buys extrapolation powers
- 14 Trivial existence cases
- 15 Playing with the function family
- 16 Invariant representation
- 17 Finding the relevant variables
- 18 Invariance and causation
- 19 Invariance for causal inference
- 20 Invariant causal prediction
- 21 Adversarial Domain Adaptation
- 22 4- Robust supervised learning
- 23 The linear least square case
- 24 Issues
- 25 Characterization of the solutions
- 26 Rank of the feature matrix S
- 27 Exact recovery of high rank solutions Two set of environments
- 28 Nonlinear version
- 29 Colored MNIST
- 30 Scaling up invariant regularization
- 31 Phenomenon and interpretation
