# View Source Axon.Schedules (Axon v0.4.1)

Parameter Schedules.

Parameter schedules are often used to anneal hyperparameters such as the learning rate during the training process. Schedules provide a mapping from the current time step to a learning rate or another hyperparameter.

Choosing a good learning rate and consequently a good learning rate schedule is typically a process of trial and error. Learning rates should be relatively small such that the learning curve does not oscillate violently during the training process, but not so small that learning proceeds too slowly. Using a schedule slowly decreases oscillations during the training process such that, as the model converges, training also becomes more stable.

All of the functions in this module are implemented as
numerical functions and can be JIT or AOT compiled with
any supported `Nx`

compiler.

# Link to this section Summary

## Functions

Constant schedule.

Cosine decay schedule.

Exponential decay schedule.

Linear decay schedule.

Polynomial schedule.

# Link to this section Functions

Constant schedule.

$$\gamma(t) = \gamma_0$$

Cosine decay schedule.

$$\gamma(t) = \gamma_0 * \left(\frac{1}{2}(1 - \alpha)(1 + \cos\pi \frac{t}{k}) + \alpha\right)$$

##
options

Options

`:decay_steps`

- number of steps to apply decay for. $k$ in above formulation. Defaults to`10`

`:alpha`

- minimum value of multiplier adjusting learning rate. $\alpha$ in above formulation. Defaults to`0.0`

##
references

References

Exponential decay schedule.

$$\gamma(t) = \gamma_0 * r^{\frac{t}{k}}$$

##
options

Options

`:decay_rate`

- rate of decay. $r$ in above formulation. Defaults to`0.95`

`:transition_steps`

- steps per transition. $k$ in above formulation. Defaults to`10`

`:transition_begin`

- step to begin transition. Defaults to`0`

`:staircase`

- discretize outputs. Defaults to`false`

Linear decay schedule.

##
options

Options

`:warmup`

- scheduler warmup steps. Defaults to`0`

`:steps`

- total number of decay steps. Defaults to`1000`

Polynomial schedule.

$$\gamma(t) = (\gamma_0 - \gamma_n) * (1 - \frac{t}{k})^p$$

##
options

Options

`:end_value`

- end value of annealed scalar. $\gamma_n$ in above formulation. Defaults to`1.0e-3`

`:power`

- power of polynomial. $p$ in above formulation. Defaults to`2`

`:transition_steps`

- number of steps over which annealing takes place. $k$ in above formulation. Defaults to`10`