The fundamental intuition behind a piecewise constant learning rate schedule is to allow the optimization process to proceed with a steady learning rate until it reaches a stationary point or plateau regarding the distribution of weight vectors. By abruptly dropping the learning rate only after efficiently converging to this suitable solution, the model reduces the inherent variance of its parameters. This approach enables the discovery of a higher quality proxy to a good local minimum and slightly better overall solutions.

Intuition Behind Piecewise Constant Learning Rate Schedules

A multi-factor (or piecewise constant) learning rate scheduler decreases the learning rate by a specific factor at predefined milestone epochs. While modern frameworks offer built-in solutions—such as `torch.optim.lr_scheduler.MultiStepLR` in PyTorch and `lr_scheduler.MultiFactorScheduler` in MXNet—this strategy can also be implemented from scratch. The following Python code demonstrates a custom scheduler that multiplies the base learning rate by a given factor whenever the current epoch is found in the predefined set of milestone steps:

```python
class MultiFactorScheduler:
    def __init__(self, step, factor, base_lr):
        self.step = step
        self.factor = factor
        self.base_lr = base_lr

    def __call__(self, epoch):
        if epoch in self.step:
            self.base_lr = self.base_lr * self.factor
            return self.base_lr
        else:
            return self.base_lr
```

Multi-Factor Learning Rate Scheduler Implementation

To stabilize optimization and achieve better convergence during fine-tuning, a step learning rate scheduler is often employed to periodically reduce the learning rate. By defining a period (lr_period) and a decay factor (lr_decay), tools like torch.optim.lr_scheduler.StepLR automatically multiply the learning rate by the decay factor after every specified number of epochs, ensuring smaller optimization steps as the model approaches a local minimum on the target dataset.

Step Learning Rate Scheduler in Fine-Tuning

To train the image classification model and select optimal hyperparameters based on validation set performance, a comprehensive training function is defined. This function orchestrates the training loop over a specified number of epochs using data parallelism across multiple devices. It initializes an optimization algorithm, such as stochastic gradient descent (SGD) with momentum and weight decay, and incorporates a step learning rate scheduler to periodically decay the learning rate by a specified factor. Within each epoch, the function iterates through training mini-batches to update parameters and accumulate training loss and accuracy. If a validation iterator is provided, it evaluates the model's accuracy on the hold-out validation set, plotting these metrics dynamically to monitor the model's generalization progress.

CIFAR-10 Model Training Function Definition

A piecewise constant learning rate schedule, often referred to as a multi-factor scheduler, maintains a steady learning rate for predefined intervals of training and abruptly drops the rate at specific milestones. Mathematically, given a set of milestone times $$s$$ (such as $$s = \{5, 10, 20\}$$), the learning rate is updated according to the rule $$\eta_{t+1} \leftarrow \eta_t \cdot \alpha$$ whenever the current step $$t \in s$$, where $$\alpha$$ is the designated decay factor.

Claude

A learning rate scheduler is a mechanism used to dynamically adjust the learning rate during the training of a model. Rather than keeping the learning rate constant, the scheduler acts as a function that takes the number of optimization updates (such as iterations or epochs) and outputs the appropriate learning rate value for the next step.

Learning Rate Scheduler

Dive into Deep Learning

Applying a learning rate scheduler to gently decrease the learning rate over the course of training can lead to improved model accuracy and less overfitting compared to using a constant learning rate. While the exact cause is debated, one theoretical explanation suggests that taking smaller step sizes forces the model parameters to remain closer to zero, resulting in a simpler model, although this does not completely explain the phenomenon.

Effect of Learning Rate Scheduling on Overfitting

A polynomial learning rate decay schedule gradually reduces the learning rate over the course of training according to a polynomial function. It is considered one of the common policy choices for dynamically adjusting the learning rate.

Polynomial Learning Rate Decay

Piecewise Constant Learning Rate Schedule

A cosine learning rate schedule, proposed by Loshchilov and Hutter (2016), dynamically adjusts the learning rate by following the shape of a cosine curve. It relies on the observation that the learning rate should not decrease too drastically at the beginning of training, and that the solution should be refined at the end using a very small learning rate. For learning rates in the range $$t \in [0, T]$$, this results in a schedule with the functional form:

$$\eta_t = \eta_T + \frac{\eta_0 - \eta_T}{2} \left(1 + \cos(\pi t/T)\right)$$

Here, $$\eta_0$$ is the initial learning rate and $$\eta_T$$ is the target rate at the maximum update step $$T$$. For steps $$t > T$$, the learning rate is simply pinned to $$\eta_T$$ without increasing it again.

Cosine Learning Rate Schedule

To address the dilemma of choosing an initial learning rate that is either too small (causing slow progress) or too large (causing divergence), a simple strategy called optimizer warmup is used. During a warmup period, the learning rate gradually increases—typically linearly—from a small value to its initial maximum, after which it cools down until the end of the optimization process.

Optimizer Warmup

A factor learning rate scheduler is an alternative to polynomial decay that utilizes a multiplicative reduction strategy. The learning rate is updated at each step using the equation $$\eta_{t+1} \leftarrow \eta_t \cdot \alpha$$, where $$\alpha \in (0, 1)$$. To prevent the learning rate from decaying beyond a reasonable lower bound, the update equation is typically modified to $$\eta_{t+1} \leftarrow \mathop{\mathrm{max}}(\eta_{\mathrm{min}}, \eta_t \cdot \alpha)$$.

Factor Learning Rate Scheduler

A basic learning rate adjustment can be performed explicitly at each step by modifying the optimizer's parameter groups directly. The following Python code demonstrates how to set a new learning rate manually in a PyTorch optimizer:

```python
lr = 0.1
trainer.param_groups[0]["lr"] = lr
print(f'learning rate is now {trainer.param_groups[0]["lr"]:.2f}')
```

Explicit Learning Rate Adjustment Implementation

To empirically study learning rate scheduling, a computationally efficient yet nontrivial toy problem can be constructed. A common setup involves training a modernized LeNet architecture on the Fashion-MNIST dataset. This modernized LeNet updates the classic design by replacing sigmoid activations with ReLU activations and substituting AveragePooling operations with MaxPooling.

Learning Rate Scheduler Toy Problem

A simple learning rate scheduler can be defined to decay the learning rate proportionally to the inverse square root of the number of updates. Specifically, at step $$t$$, the learning rate is set to $$\eta = \eta_0 (t + 1)^{-\frac{1}{2}}$$, where $$\eta_0$$ is the initial learning rate. This formulation ensures that the step size gently and continuously decreases as training progresses.

Learn Before

Related

Learn After