Hyperparameter Tuning

Experiment with automated search strategies. Use Grid Search to systematically scan parameters or Random Search to find high-performance zones efficiently.

0.03
4

Tuning Dashboard

READY
Trial Status
-- / --
Best Accuracy
0.0%

Search History

# LR Nodes Accuracy
Start a search to see trials.
Drag to Pan | Scroll to Zoom

Hyperparameter Tuning: Complete Guide

The knobs you adjust outside of gradient descent that determine whether training succeeds or fails.

Quick Context

Hyperparameters are settings defined before training begins — learning rate, batch size, number of layers, dropout rate, etc. Unlike model parameters (weights), they are not learned via gradient descent. Choosing good hyperparameters can be the difference between a model that converges in 10 minutes and one that never converges at all.

1) Parameters vs. Hyperparameters

  • Parameters (weights, biases): learned automatically during training via backpropagation.
  • Hyperparameters (learning rate, batch size, architecture choices): set by you before training. They control how learning happens.

2) Key Hyperparameters and Their Effects

  • Learning Rate — the single most important hyperparameter. Too high → divergence. Too low → slow convergence. Start with 1e-3 for Adam, 1e-2 for SGD.
  • Batch Size — larger batches = smoother gradients but less regularization. Smaller batches = noisier but better generalization. Common: 32, 64, 128, 256.
  • Number of Layers/Neurons — more capacity = can learn more complex patterns but also overfit more easily.
  • Dropout Rate — typically 0.1–0.5. Higher = more regularization. Too high = underfitting.
  • Weight Decay (L2) — penalizes large weights. Typical: 1e-4 to 1e-2.
  • Number of Epochs — combined with early stopping; set high and let early stopping decide when to stop.

3) Tuning Strategies

  • Grid Search — try every combination of predefined values. Exhaustive but exponentially expensive. Only practical with 2–3 hyperparameters.
  • Random Search — sample random combinations. Surprisingly effective because most hyperparameters have different sensitivities — random search explores more distinct values per parameter.
  • Bayesian Optimization — builds a probabilistic model of the objective function and intelligently picks the next set of hyperparameters. Tools: Optuna, Hyperopt, Weights & Biases Sweeps.
  • Manual Tuning — start with known good defaults, change one thing at a time, observe the result. Requires experience but is fast for simple problems.

4) Guided Experiments

  1. Start with default hyperparameters and observe baseline performance.
  2. Change only the learning rate — try 0.1, 0.01, 0.001, 0.0001 and compare loss curves.
  3. With the best LR, now vary batch size — notice how the loss curve smoothness changes.
  4. Add dropout with different rates — observe the gap between training and validation loss (smaller gap = less overfitting).

5) Common Mistakes

  • Tuning multiple things at once — you can't tell what helped. Change one at a time.
  • Tuning on the test set — this is data leakage. Use a validation set; touch the test set only once.
  • Spending too long on grid search — random search with the same budget usually finds better results.
  • Ignoring the learning rate — most training failures are learning rate problems.

6) Key Takeaways

  • Hyperparameters control training behavior and must be set before learning begins.
  • Learning rate is the most impactful — always tune it first.
  • Random search is more efficient than grid search for most problems.
  • Always validate on a held-out set, never the test set.
Cheat sheet

Hyperparameter Tuning

Experiment with automated search strategies. Use Grid Search to systematically scan parameters or Random Search to find high-performance zones efficiently.

DEEP LEARNING · vizlearn.in/deep_learning/hyper-paramter_tuning.html