liveBook · Manning

Batch gradient descent

As explained in Build AI Drug Discovery Pipelines

Batch gradient descent is an optimization method that computes each parameter update from the entire training dataset.

Batch gradient descent updates model parameters by computing the gradient from the entire training dataset. Its steps become smaller as the cost approaches a minimum, with learning rate controlling convergence behavior. section 4.2.3

Practical training requires monitoring several factors:

  • Combine a large iteration limit, an acceptable cost threshold, and a marginal-cost-decrease threshold to decide when to stop. section 4.2.3
  • Compare batch updates with stochastic and mini-batch methods, which reduce per-update data requirements but produce noisier convergence. section 4.2.3 section 4.5
  • Scale features when different variable magnitudes would cause some variables to dominate training. section 4.2.3

Molecular solubility

A linear model trained on AqSolDB can use molecular descriptors to characterize solubility, a drug-discovery property linked to absorption and dosing. Batch gradient descent provides an iterative alternative to the normal equation for finding model weights. section 4.5

Figure 4.11 Impact of learning step size on the ability for gradient descent to converge.

Use the convergence illustration to inspect how learning-step size affects whether gradient descent reaches a minimum. section 4.2.3

How Build AI Drug Discovery Pipelines covers it

How deep it goes
Explains full-dataset updates, step-size behavior, stopping criteria, scaling, and gradient clipping without presenting implementation code.
Examples
Uses AqSolDB molecular-solubility modeling and illustrations of cost surfaces, step sizes, stopping criteria, and feature scaling.
What you can do after
Evaluate iterative optimization choices by comparing convergence, runtime, memory use, and parameter-quality tradeoffs.
How it connects
Connects gradient descent with linear regression, the normal equation, stochastic gradient descent, mini-batch training, feature scaling, and gradient clipping.

Also explained in

Compare how 2 books explain batch gradient descent →

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Build AI Drug Discovery Pipelines. The section links point to the parts of the book it draws on.