How deeply does Sutskever's List cover momentum?

Explains momentum through noisy steps and a hiking analogy, but gives no mathematical update rule.

Momentum

Momentum is an optimization technique that incorporates a running history of parameter updates to smooth and accelerate training.

Momentum carries a running history of parameter updates into later steps. In mini-batch SGD, where each batch gives a noisy estimate of the downhill direction, averaging recent steps can reduce sideways jitter and help progress across shallow plateaus. section 2.5.4

A hiker in fog

A hiker can see only a small patch of a mountain and may misjudge the downhill direction. Momentum acts like inertia: instead of reacting sharply to each new patch, the hiker carries recent steps forward, gliding through plateaus and avoiding some sideways jitter. section 2.5.4

AlexNet used momentum of 0.9 with mini-batch SGD and batches of 128 images. It was one part of a larger set of training choices—including ReLU activations, weight initialization, dropout, and data augmentation—that helped make deep learning work at scale. section 2.5.4 section 2.5.5

How Sutskever's List covers it

liveBook manning.com

Read Sutskever's List on liveBook Get the book at manning.com

Also explained in

liveBook manning.com

Inside Deep Learning: Math, Algorithms, ModelsA stochastic gradient-based optimization method that uses an accumulated velocity term for parameter updates.
liveBook manning.com

Math and Architectures of Deep LearningAn optimization strategy that accelerates parameter updates using accumulated past gradients or a lookahead variant to smooth descent on the loss surface.
liveBook manning.com

Natural Language Processing in Action, Second EditionMomentum is an optimization hyperparameter that incorporates prior update direction to accelerate or damp parameter movement during gradient-based optimization.
liveBook manning.com

Deep Learning with R, Third EditionMomentum is an optimization technique that incorporates previous parameter updates into the current update to improve movement through the optimization landscape.
liveBook manning.com

Machine Learning Algorithms in DepthMomentum is an optimization technique that incorporates an exponentially weighted moving average of past gradients into parameter updates.

Compare how 6 books explain momentum →

Related concepts

adamused by · Adam is an adaptive stochastic-gradient optimization algorithm that updates model parameters using moving estimates of the first and second moments of gradients.
inner productuses · An inner product is a scalar-valued operation on two vectors that combines their corresponding components, summing their products and, for complex vectors, using conjugation.
stochastic gradient descentconfigures · Stochastic gradient descent is an iterative optimization method that updates parameters using gradients estimated from individual examples or randomly selected small batches.
partial derivativeequivalent to · A partial derivative is the derivative of a multivariable function with respect to one variable while holding the other variables constant.
batch sizeuses · Batch size is the number of items grouped together for processing or computation as a single batch.
Nesterov momentumincludes · Nesterov momentum is an optimization method that evaluates the gradient at a momentum-based lookahead position before updating model parameters.

This explainer was generated by Manning's knowledge graph from the text of Sutskever's List. The section links point to the parts of the book it draws on.