Material Detail

Randomized PCA Algorithms with Regret Bounds that are Logarithmic in the Dimension

Randomized PCA Algorithms with Regret Bounds that are Logarithmic in the Dimension

This video was recorded at Machine Learning Summer School (MLSS), Taipei 2006. We design an on-line algorithm for Principal Component Analysis. The instances are projected into a probabilistically chosen low dimensional subspace. The total expected quadratic approximation error equals the total quadratic approximation error of the best subspace chosen in hindsight plus some additional term that grows linearly in dimension of the subspace but logarithmically in the dimension of the instances.

Quality

  • User Rating
  • Comments
  • Learning Exercises
  • Bookmark Collections
  • Course ePortfolios
  • Accessibility Info

More about this material

Comments

Log in to participate in the discussions or sign up if you are not already a MERLOT member.