Skip to content
Free standard shipping to supported destinations
Delta-Xi LogoDelta Xi
ShopOur storyLearnHelp
Learn
OverviewConcepts
Back to Concepts
🔄
Algorithmsalgorithm

Gradient descent

Adjust parameters in a direction that locally reduces a loss.

θk+1=θk−η∇L(θk)\theta_{k+1}=\theta_k-\eta\nabla L(\theta_k)θk+1​=θk​−η∇L(θk​)

Library note. Check the assumptions and further reading before applying a formula.

What Is This?

A loss function measures how poorly a set of parameters performs. Its gradient points toward the steepest local increase. Gradient descent takes a step in the opposite direction. The step size, eta, controls how far it moves. Repeat the calculation at the new point. The method uses local slope information, not a map of the whole landscape.

Try an example

For L(theta) = theta squared, the gradient is 2 theta. Starting at theta = 3 with a step size of 0.1, the next value is 3 minus 0.1 times 6, or 2.4.

Where it needs care

A step that is too large can increase the loss or diverge. Non-convex functions can have local minima and saddle points. A small training loss does not establish performance on new data.

Historical Context

Cauchy described an early steepest-descent method in 1847. Stochastic variants later made the approach practical for large datasets.

Real-World Applications

  • Fit regression models and neural networks.
  • Solve differentiable numerical optimisation problems.

Further reading

  • Further reading: Gradient descent
Difficulty:Intermediate
Delta-Xi LogoDelta Xi

A place for good ideas, on a shirt or off the page.

Say hello

Explore

  • Shop all
  • Mathematics T-shirts
  • Accessories
  • Learn
  • Our story

Here to help

  • Contact
  • Size & care questions
  • Shipping & returns
  • Your orders
  • Track an order

Keep in touch

  • Instagram
  • Discord
  • Telegram
  • Affiliate programme

© 2026 Delta Xi. Prices in USD.

PrivacyTerms

Your cookie choices

Essential cookies keep your basket and sign-in working. Optional cookies help us understand visits and measure ads. Privacy details.

Related Concepts

🔄

Big O Notation

A mathematical notation that describes the limitin

🔄

Binary Search

Search algorithm that finds the position of a targ

🔄

Dijkstra's Algorithm

Finds the shortest paths between nodes in a weight