Closed secondsensei closed 1 year ago
Y should be in shape [n_features, n_samples], which mean each column is a sample.
k and lambda should be chosen based on each problem and data. k must be << n_samples lambda should be < 1 (0.1, 0.01).
I don't have matlab now, not sure how I could assist you.
Thanks for the response. What about the 'opts' input? What can I input for 'opts'? ODL(Y, k, lambda, opts, 'fista')
Please see the source code for more information.
Y is a size 2000x50 matrix. Should this be transposed?
k, and lambda are defined variables. What are my options for opts?
`>> ODL(Y, k, lambda, opts, 'fista') Unable to perform assignment because dot indexing is not supported for variables of this type.
Error in initOpts (line 14) opts.verbose = 0;
Error in ODL (line 36) opts = initOpts(opts);`
When I ran the function. I got this error. Please assist