Statistics – Machine Learning
Scientific paper
2011-03-27
Statistics
Machine Learning
26 pages, 1 figure
Scientific paper
We theoretically investigate the convergence rate and support consistency (i.e., correctly identifying the subset of non-zero coefficients in the large sample limit) of multiple kernel learning (MKL). We focus on MKL with block-l1 regularization (inducing sparse kernel combination), block-l2 regularization (inducing uniform kernel combination), and elastic-net regularization (including both block-l1 and block-l2 regularization). For the case where the true kernel combination is sparse, we show a sharper convergence rate of the block-l1 and elastic-net MKL methods than the existing rate for block-l1 MKL. We further show that elastic-net MKL requires a milder condition for being consistent than block-l1 MKL. For the case where the optimal kernel combination is not exactly sparse, we prove that elastic-net MKL can achieve a faster convergence rate than the block-l1 and block-l2 MKL methods by carefully controlling the balance between the block-l1and block-l2 regularizers. Thus, our theoretical results overall suggest the use of elastic-net regularization in MKL.
Sugiyama Masashi
Suzuki Taiji
Tomioka Ryota
No associations
LandOfFree
Sharp Convergence Rate and Support Consistency of Multiple Kernel Learning with Sparse and Dense Regularization does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Sharp Convergence Rate and Support Consistency of Multiple Kernel Learning with Sparse and Dense Regularization, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Sharp Convergence Rate and Support Consistency of Multiple Kernel Learning with Sparse and Dense Regularization will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-94773