Yixuan Qiu

I haven't investigated this yet, but notebooks need more HTML elements such as buttons and tabs, so it may be a separate project rather than working on existing `prettydoc` themes.

Hi @hyl317, the error message is about the line search procedure, not the overall iterations. The parameter to control it is `param.max_linesearch`.

I sincerely thank all the comments and suggestions to make LBFGS++ a better library. One thing I have to say sorry is that I'm indeed quite busy these days and...

Most of the issues have been fixed by @mpayrits in https://github.com/yixuan/LBFGSpp/pull/25, and I'm looking deeper at the Moré-Thuente paper to see if there is any additional bug in the code.

I've dug into the paper a little deeper, and now I feel more confident to answer some of the questions raised by @mpayrits. For the `phi/psi` issue, I have actually...

Hi @izsahara, do you have any test cases to compare the results?

Thanks @cschreib-ibex for the careful investigation. Indeed, these parameters can somehow be mapped to the Scipy default, but from my own experience, it is pretty hard to exactly reproduce the...

Yeah, I'm thinking of how to refactor the code and properly return from the line search routine. I'll update here once I have any progress.

Unfortunately MiniDNN has not yet implemented padding types other than the "valid" rule. It is indeed some tedious work to write such low-level functions, and probably you should take a...

Yeah, my feeling is that transposing the data set is a much cheaper operation than the training and prediction process. Some of the internal operators are indeed hard-coded using the...