Regression: objectives and metrics
Objectives and metrics
MAE
Usage information See more.
User-defined parameters
use_weights
Use object/group weights to calculate metrics if the specified value is true
and set all weights to 1
regardless of the input data if the specified value is false
.
Default: true
MAPE
Usage information See more.
User-defined parameters
use_weights
Use object/group weights to calculate metrics if the specified value is true
and set all weights to 1
regardless of the input data if the specified value is false
.
Default: true
Poisson
Usage information See more.
User-defined parameters
use_weights
Use object/group weights to calculate metrics if the specified value is true
and set all weights to 1
regardless of the input data if the specified value is false
.
Default: true
Quantile
Usage information See more.
User-defined parameters
use_weights
Use object/group weights to calculate metrics if the specified value is true
and set all weights to 1
regardless of the input data if the specified value is false
.
Default: true
alpha
The coefficient used in quantile-based losses.
Default: 0.5
MultiQuantile
Usage information See more.
User-defined parameters
use_weights
Use object/group weights to calculate metrics if the specified value is true
and set all weights to 1
regardless of the input data if the specified value is false
.
Default: true
alpha
The vector of coefficients used in multi-quantile loss.
Default: 0.5
RMSE
Usage information See more.
User-defined parameters
use_weights
Use object/group weights to calculate metrics if the specified value is true
and set all weights to 1
regardless of the input data if the specified value is false
.
Default: true
RMSEWithUncertainty
,
where is target, a 2-dimensional approx is target predict, is predict, and is the probability density function of the normal distribution.
See the Uncertainty section for more details.
Usage information See more.
User-defined parameters
use_weights
Use object/group weights to calculate metrics if the specified value is true
and set all weights to 1
regardless of the input data if the specified value is false
.
Default: true
LogLinQuantile
Depends on the condition for the ratio of the label value and the resulting value:
Usage information See more.
User-defined parameters
use_weights
Use object/group weights to calculate metrics if the specified value is true
and set all weights to 1
regardless of the input data if the specified value is false
.
Default: true
alpha
The coefficient used in quantile-based losses.
Default: 0.5
Lq
Usage information See more.
User-defined parameters
use_weights
Use object/group weights to calculate metrics if the specified value is true
and set all weights to 1
regardless of the input data if the specified value is false
.
Default: true
q
The power coefficient.
Valid values are real numbers in the following range:
Default: Obligatory parameter
Huber
User-defined parameters:
delta
The parameter of the Huber metric.
Default: Obligatory parameter
Usage information See more.
User-defined parameters
use_weights
Use object/group weights to calculate metrics if the specified value is true
and set all weights to 1
regardless of the input data if the specified value is false
.
Default: true
Expectile
Usage information See more.
User-defined parameters
use_weights
Use object/group weights to calculate metrics if the specified value is true
and set all weights to 1
regardless of the input data if the specified value is false
.
Default: true
alpha
The coefficient used in expectile-based losses.
Default: 0.5
Tweedie
is the value of the variance_power parameter.
Labels should be non-negative.
Large labels may cause numerical overflows and/or divergence when training a tweedie regression model.
On CPU, it is recommended to scale labels to range .
On GPU, it is recommended to scale lables to range .
Usage information See more.
User-defined parameters
use_weights
Use object/group weights to calculate metrics if the specified value is true
and set all weights to 1
regardless of the input data if the specified value is false
.
Default: true
variance_power
The variance of the Tweedie distribution.
Supported values are in the range (1;2).
Default: Obligatory parameter
LogCosh
Usage information See more.
User-defined parameters
use_weights
Use object/group weights to calculate metrics if the specified value is true
and set all weights to 1
regardless of the input data if the specified value is false
.
Default: true
FairLoss
is the value of the smoothness parameter.
Can't be used for optimization. See more.
User-defined parameters
use_weights
Use object/group weights to calculate metrics if the specified value is true
and set all weights to 1
regardless of the input data if the specified value is false
.
Default: true
use_weights
The smoothness coefficient. Valid values are real values in the following range .
Default: 1.0
NumErrors
The proportion of predictions, for which the difference from the label value exceeds the specified value greater_than.
User-defined parameters: greater_than
Can't be used for optimization. See more.
User-defined parameters
use_weights
Use object/group weights to calculate metrics if the specified value is true
and set all weights to 1
regardless of the input data if the specified value is false
.
Default: true
SMAPE
Can't be used for optimization. See more.
User-defined parameters
use_weights
Use object/group weights to calculate metrics if the specified value is true
and set all weights to 1
regardless of the input data if the specified value is false
.
Default: true
R2
is the average label value:
Can't be used for optimization. See more.
User-defined parameters
use_weights
Use object/group weights to calculate metrics if the specified value is true
and set all weights to 1
regardless of the input data if the specified value is false
.
Default: true
MSLE
Can't be used for optimization. See more.
User-defined parameters
use_weights
Use object/group weights to calculate metrics if the specified value is true
and set all weights to 1
regardless of the input data if the specified value is false
.
Default: true
MedianAbsoluteError
Can't be used for optimization. See more.
User-defined parameters
No.
Cox
Labels mean occurence of the event at time , and labels mean absence of the event at time .
Predictions are hazard rates.
Usage information See more.
User-defined parameters
No.
SurvivalAft
Observation interval is for , and for .
Predictions are hazard rates.
Helper for , and , is hazard prediction error.
Coefficient is scale of hazard prediction error, specified by scale parameter.
Functions and are probability density and cumulative distribution, specified by dist parameter.
dist
Guessed distribution of hazard prediction error.
Possible values: Normal, Extreme, Logistic.
dist |
||
|---|---|---|
Normal |
||
Logistic |
||
Extreme |
Default: Normal
scale
Scale of hazard prediction error.
Default: 1.0
Usage information See more.
User-defined parameters
No.
Used for optimization
| Name | Optimization | GPU Support |
|---|---|---|
| MAE | + | + |
| MAPE | + | + |
| Poisson | + | + |
| Quantile | + | + |
| MultiQuantile | + | - |
| RMSE | + | + |
| RMSEWithUncertainty | + | + |
| LogLinQuantile | + | + |
| Lq | + | + |
| Huber | + | + |
| Expectile | + | + |
| Tweedie | + | + |
| LogCosh | + | - |
| Cox | + | - |
| SurvivalAft | + | - |
| FairLoss | - | - |
| NumErrors | - | + |
| SMAPE | - | - |
| R2 | - | - |
| MSLE | - | - |
| MedianAbsoluteError | - | - |