Material Detail

Bandit-Based Optimization on Graphs with Application to Library Performance Tuning

Bandit-Based Optimization on Graphs with Application to Library Performance Tuning

This video was recorded at 26th International Conference on Machine Learning (ICML), Montreal 2009. The problem of choosing fast implementations for a class of recursive algorithms such as the fast Fourier transforms can be formulated as an optimization problem over the language generated by a suitably defined grammar. We propose a novel algorithm that solves this problem by reducing it to maximizing an objective function over the sinks of a directed acyclic graph. This algorithm valuates nodes using Monte-Carlo and grows a subgraph in the most promising directions by considering local maximum k-armed bandits. When used inside an adaptive linear transform library, it cuts down the search time by an order of magnitude compared to the existing algorithm. In some cases, the performance of the... Show More
Rate

Quality

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

More about this material

Browse...

Disciplines with similar materials as Bandit-Based Optimization on Graphs with Application to Library Performance Tuning

Comments

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