verne.freenode.net changed the topic of #mlpack to: http://www.mlpack.org/ -- We don't respond instantly... but we will respond. Give it a few minutes. Or hours. -- Channel logs: http://www.mlpack.org/irc/
< tham>
zoq : I do it as you suggest and measure the performance again
< tham>
iterative algo work faster if row == col or row << col
< tham>
2000 * 2000, times are 1026568 vs 7419391 if you need 5 eigen vectors
< tham>
1000 * 2000, 204803 vs 2930917
< tham>
slower than randomize solution
< tham>
not worth to add into mlpack
Mathnerd314 has quit [Ping timeout: 252 seconds]
Aterons has joined #mlpack
tham has quit [Quit: Page closed]
mentekid has joined #mlpack
< zoq>
tham: okay, thanks for the information, we could use the iterative approach if it's faster if m=n, but I think once the quic-svd method works in that case, it would be faster.