MomentumStep¶
Chainable step that adds momentum based on one of several formulations, including classic momentum, Nesterov acceleration, and exponential moving average.
This can improve the convergence behavior of the optimizer, including the convergence rate (esp. when nesterov acceleration is used) and the ability to escape saddle points. Version 0.2.0
Ports/Properties¶
gradients¶
Gradients to be transformed.
weights¶
Optional current weights.
state¶
Explicit state of the node.
decay¶
Exponential decay rate for past values.
type¶
Type of momentum to use. Momentum is classic momentum, Nesterov is Nesterov acceleration, and EMA is exponential moving average.
mu_precision¶
Numeric precision for the first-order accumulator. Keep resolves to the precision of the inputs.
set_breakpoint¶
Set a breakpoint on this node. If this is enabled, your debugger (if one is attached) will trigger a breakpoint.
metadata¶
User-definable meta-data associated with the node. Usually reserved for technical purposes.