Is there a gurobi product to optimize a function on the dataset consisting of 600000 observations ?

回答済み

Ilona Hatossy

2020年06月24日 08:27

• 
• 

I have to find the value of x that optimizes the following:

f(xi) = SUM(ai(1+xi/100) - bi)*(1-yi)

where 
yi = exp(ci + di*xi)/(1+exp(ci+di*xi)
under the constraint that
yi <=CONSTANT

ai, bi, ci, di are the parameters different for i=1 to n=600000 observations

 

0

• 正式なコメント

  

  Simranjit Kaur

  • Gurobi Staff

  2025年06月23日 03:10 編集済み

  This post is more than three years old. Some information may not be up to date. For current information, please check the Gurobi Documentation or Knowledge Base. If you need more help, please create a new post in the community forum. Or why not try our AI Gurobot?.
• 

  Eli Towle

  • Gurobi Staff

  2020年06月24日 17:29

  Hi Ilona,

  Gurobi doesn't directly support terms like \( e^x \). That said, you could try building a piecewise-linear approximation of the nonlinear constraints on the \( y^i \) variables. Gurobi even supplies shortcut methods for building approximations of popular nonlinear functions, such as Model.addGenConstrExp() in the Python API.

  See here for information about the types of models Gurobi is able to solve.

  Thanks,

  Eli

  0

投稿コメントは受け付けていません。