Microsoft, DP Technology & Tsinghua U Enable Efficient Low-Precision Training of Gradient Boosting Decision Trees
In the new paper Quantized Training of Gradient Boosting Decision Trees, a team from Microsoft Research, DP Technology and Tsinghua University proposes a method for the low-precision training of gr...
Source: syncedreview.com
In the new paper Quantized Training of Gradient Boosting Decision Trees, a team from Microsoft Research, DP Technology and Tsinghua University proposes a method for the low-precision training of gradient boosting decision trees via gradient quantization.