> ## Documentation Index
> Fetch the complete documentation index at: https://nixtlaverse.nixtla.io/llms.txt
> Use this file to discover all available pages before exploring further.

# Optimization Objectives

NeuralForecast is a highly modular framework capable of augmenting a
wide variety of robust neural network architectures with different point
or probability outputs as defined by their optimization objectives.

## Point losses

| Scale-Dependent | Percentage-Errors | Scale-Independent | Robust |
| :- | :- | :- | :- |
| [**MAE**](../../losses.pytorch.html#mae) | [**MAPE**](../../losses.pytorch.html#mape) | [**MASE**](../../losses.pytorch.html#mase) | [**Huber**](../../losses.pytorch.html#huber-loss) |
| [**MSE**](../../losses.pytorch.html#mse) | [**sMAPE**](../../losses.pytorch.html#smape) | | [**Tukey**](../../losses.pytorch.html#tukeyloss) |
| [**RMSE**](../../losses.pytorch.html#rmse) | | | [**HuberMQLoss**](../../losses.pytorch.html#hubermqloss) |

## Probabilistic losses

| Parametric Probabilities | Non-Parametric Probabilities |
| :- | :- |
| [**Normal**](../../losses.pytorch.html#distributionloss) | [**QuantileLoss**](../../losses.pytorch.html#quantileloss) |
| [**StudenT**](../../losses.pytorch.html#distributionloss) | [**MQLoss**](../../losses.pytorch.html#mqloss) |
| [**Poisson**](../../losses.pytorch.html#distributionloss) | [**HuberQLoss**](../../losses.pytorch.html#huberiqloss) |
| [**Negative Binomial**](../../losses.pytorch.html#distributionloss) | [**HuberMQLoss**](../../losses.pytorch.html#hubermqloss) |
| [**Tweedie**](../../losses.pytorch.html#distributionloss) | [**IQLoss**](../../losses.pytorch.html#iqloss) |
| [**PMM**](../../losses.pytorch.html#pmm) | [**HuberIQLoss**](../../losses.pytorch.html#huberiqloss) |
| [**GMM**](../../losses.pytorch.html#gmm) | [**ISQF**](../../losses.pytorch.html#isqf) |
| [**NBMM**](../../losses.pytorch.html#nbmm) | |


## Related topics

- [Weighting Timesteps | NeuralForecast](/neuralforecast/docs/tutorials/weighting_timesteps.html.md)
- [PyTorch Losses](/neuralforecast/losses.pytorch.html.md)
- [Optimization](/mlforecast/optimization.html.md)
- [HINT](/neuralforecast/models.hint.html.md)
- [Multi-Objective Model Selection with Pareto Frontier](/utilsforecast/docs/tutorials/multi_objective_model_selection.html.md)