The inverse Potts problem to infer a Boltzmann distribution for homologous protein sequences
from their single-site and pairwise amino acid frequencies recently attracts a great deal of attention
in the studies of protein structure and evolution.  We study regularization and learning methods
and how to tune regularization parameters to correctly infer interactions
in Boltzmann machine learning.	Using L2 regularization for fields, group L1 for couplings
is shown to be very effective for sparse couplings in comparison with L2 and 
L1.  Two regularization parameters are tuned to yield equal values for both
the sample and ensemble averages of evolutionary energy.  
The Adam method is modified to make stepsize proportional to the 
gradient for sparse couplings and to use a soft-thresholding function for group L1.
It is shown by first inferring interactions from protein sequences and then from Monte Carlo samples
that the fields and couplings can be well recovered, but that recovering the pairwise 
correlations in the resolution of a total energy is harder for the natural proteins than
for the protein-like sequences. Refer to DOI:10.1109/TCBB.2020.2993232 (arXiv:1909.05006).