We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
What should we name the following two classes of penalties for problems of the form
min_{coef} L(coef) + p(coef)
Perhaps someone has named these already?
p(coef) = min_{b_1, ..., b_q s.t. coef = sum_{j=1}^q b_j} sum_{j=1}^q b_j p(b_j)
which is equivalent to solving
min_{b_1, ..., b_q} L(sum_{j=1}^q b_j) + sum_{j=1}^q b_j p(b_j)
E.g. this is the low rank + sparse of (Candes et al., 2011), row sparse plus entrywise sparse of (Tan el al., 2014) or overlapping group lasso of (Jacob et al., 2009)
Ideas
Infimal sum feels most accurate e.g. it is close to the "infimal convolution" operation -- see Section 2.3.2 of FOMO
p(coef) = sum_{j=1}^q b_j} p_j (b_j)
e.g. this is the sparse group or sparse fused lasso
Ideas:
The text was updated successfully, but these errors were encountered:
No branches or pull requests
What should we name the following two classes of penalties for problems of the form
Perhaps someone has named these already?
Additive/Infimal sum
which is equivalent to solving
E.g. this is the low rank + sparse of (Candes et al., 2011), row sparse plus entrywise sparse of (Tan el al., 2014) or overlapping group lasso of (Jacob et al., 2009)
Ideas
Infimal sum feels most accurate e.g. it is close to the "infimal convolution" operation -- see Section 2.3.2 of FOMO
Fully overlapping sum
e.g. this is the sparse group or sparse fused lasso
Ideas:
The text was updated successfully, but these errors were encountered: