ExponentialLRScheduler
Models & Types ยท AiDotNet.LearningRateSchedulers
Decays the learning rate exponentially every step.
Inheritance: LearningRateSchedulerBase โ ExponentialLRScheduler
For Beginners
This scheduler smoothly reduces the learning rate at every step by multiplying it by a factor (gamma). Unlike StepLR which makes sudden drops, exponential decay provides a gradual, continuous reduction. Think of it like gradually releasing pressure from a gas pedal rather than making sudden brake taps.
How It Works
ExponentialLR decays the learning rate by gamma every step. This provides a smooth, continuous decay that can be useful for certain training scenarios.
Formula: lr = base_lr * gamma^step
Example
using AiDotNet.LearningRateSchedulers;
// Decay by 0.95 every epoch
var scheduler = new ExponentialLRScheduler(
baseLearningRate: 0.1,
gamma: 0.95
);
Constructors
| Constructor | Summary |
|---|---|
ExponentialLRScheduler(double baseLearningRate, double gamma, double minLearningRate) |
Initializes a new instance of the ExponentialLRScheduler class. |
Properties
| Property | Summary |
|---|---|
double Gamma { get; } |
Gets the multiplicative factor of learning rate decay. |
Methods
| Method | Summary |
|---|---|
Dictionary<string, object> GetState() |