timemixer_losses
chronax.timemixer_losses
Pluggable point-loss functions for the TimeMixer forecaster.
mae
chronax.timemixer_losses.mae(pred, target)
Mean absolute error: mean(|pred - target|).
| Parameter | Type | Default | Description |
|---|---|---|---|
pred |
jnp.ndarray |
- | (undocumented) |
target |
jnp.ndarray |
- | (undocumented) |
Returns: jnp.ndarray
mse
chronax.timemixer_losses.mse(pred, target)
Mean squared error: mean((pred - target)**2).
| Parameter | Type | Default | Description |
|---|---|---|---|
pred |
jnp.ndarray |
- | (undocumented) |
target |
jnp.ndarray |
- | (undocumented) |
Returns: jnp.ndarray
huber
chronax.timemixer_losses.huber(pred, target)
Huber loss with delta = 1.0. Quadratic for |r| <= 1, linear outside.
| Parameter | Type | Default | Description |
|---|---|---|---|
pred |
jnp.ndarray |
- | (undocumented) |
target |
jnp.ndarray |
- | (undocumented) |
Returns: jnp.ndarray
resolve
chronax.timemixer_losses.resolve(loss)
Return a callable loss from either a registry string or a callable.
| Parameter | Type | Default | Description |
|---|---|---|---|
loss |
str | LossFn |
- | (undocumented) |
Returns: LossFn