Testing the Manifold Hypothesis Hari Narayanan University of Washington In collaboration with Charles Fefferman and Sanjoy Mitter Princeton MIT
Manifold learning and manifold hypothesis [Kambhatla-Leen’93, Tannenbaum et al’00, Roweis-Saul’00, Belkin-Niyogi’03, Donoho-Grimes’04]
When is the Manifold Hypothesis true?
Reach of a submanifold of R n Large reach Small reach reach
Low dimensional manifolds with bounded volume and reach
Testing the Manifold Hypothesis
Sample Complexity of testing the manifold hypothesis [
Algorithmic question
Sample complexity of testing the Manifold Hypothesis
Empirical Risk Minimization
Fitting manifolds TexPoint Display
Reduction to k-means
Proving a Uniform bound for k-means
Fat-shattering dimension
Bound on sample complexity
VC dimension
Random projection
Bound on sample complexity
Fitting manifolds
Algorithmic question
Outline
(3) Generating a smooth vector bundle
Outline
(4) Generating a putative manifold
Outline
(5) Bundle map
Outline
Concluding Remarks An algorithm for testing the manifold hypothesis. Future directions: (a)Make practical and test on real data (b)Improve precision in the reach – get rid of controlled constants depending on d. (c)Better algorithms under distributional assumptions
Thank You!