Mediaspace scheduled maintenance: Aug 25, 2026 07:00 - 12:00 AM. During this time, videos will be temporarily unavailable. Check status updates.

Lecture

Gradient Descent with Momentum

In course

CS-456: Deep reinforcement learning

This course provides an overview and introduces modern methods for reinforcement learning (RL.) The course starts with the fundamentals of RL, such as Q-learning, and delves into commonly used approaches, like PPO and DQN. The course will introduce student ...

Description

This lecture covers the concept of adding a momentum term to gradient descent to speed up the process and reduce oscillations. Topics include the loss landscape, optimization methods, saddle points, and the implementation of momentum in deep learning.

Instructors (2)

Wulfram Gerstner

Wulfram Gerstner is Director of the Laboratory of Computational Neuroscience LCN at the EPFL. His research in computational neuroscience concentrates on models of spiking neurons and spike-timing dependent plasticity, on the problem of neuronal coding in single neurons and populations, as well as on the link between biologically plausible learning rules and behavioral manifestations of learning. He teaches courses for Physicists, Computer Scientists, Mathematicians, and Life Scientists at the EPFL. After studies of Physics in Tübingen and at the Ludwig-Maximilians-University Munich (Master 1989), Wulfram Gerstner spent a year as a visiting researcher in Berkeley. He received his PhD in theoretical physics from the Technical University Munich in 1993 with a thesis on associative memory and dynamics in networks of spiking neurons. After short postdoctoral stays at Brandeis University and the Technical University of Munich, he joined the EPFL in 1996 as assistant professor. Promoted to Associate Professor with tenure in February 2001, he is since August 2006 a full professor with double appointment in the School of Computer and Communication Sciences and the School of Life Sciences. Wulfram Gerstner has been invited speaker at numerous international conferences and workshops. He has served on the editorial board of the Journal of Neuroscience, Network: Computation in Neural Systems', Journal of Computational Neuroscience', and `Science'.

Caglar Gulcehre

Official source

Related concepts (30)

Four-momentum

In special relativity, four-momentum (also called momentum–energy or momenergy) is the generalization of the classical three-dimensional momentum to four-dimensional spacetime. Momentum is a vector in three dimensions; similarly four-momentum is a four-vector in spacetime. The contravariant four-momentum of a particle with relativistic energy E and three-momentum p = (px, py, pz) = γmv, where v is the particle's three-velocity and γ the Lorentz factor, is The quantity mv of above is ordinary non-relativistic momentum of the particle and m its rest mass.

Momentum

In Newtonian mechanics, momentum (: momenta or momentums; more specifically linear momentum or translational momentum) is the product of the mass and velocity of an object. It is a vector quantity, possessing a magnitude and a direction. If m is an object's mass and v is its velocity (also a vector quantity), then the object's momentum p (from Latin pellere "push, drive") is: In the International System of Units (SI), the unit of measurement of momentum is the kilogram metre per second (kg⋅m/s), which is equivalent to the newton-second.

Energy–momentum relation

In physics, the energy–momentum relation, or relativistic dispersion relation, is the relativistic equation relating total energy (which is also called relativistic energy) to invariant mass (which is also called rest mass) and momentum. It is the extension of mass–energy equivalence for bodies or systems with non-zero momentum. It can be written as the following equation: This equation holds for a body or system, such as one or more particles, with total energy E, invariant mass m0, and momentum of magnitude p; the constant c is the speed of light.

Gradient descent

In mathematics, gradient descent (also often called steepest descent) is a iterative optimization algorithm for finding a local minimum of a differentiable function. The idea is to take repeated steps in the opposite direction of the gradient (or approximate gradient) of the function at the current point, because this is the direction of steepest descent. Conversely, stepping in the direction of the gradient will lead to a local maximum of that function; the procedure is then known as gradient ascent.

Angular momentum

In physics, angular momentum (sometimes called moment of momentum or rotational momentum) is the rotational analog of linear momentum. It is an important physical quantity because it is a conserved quantity – the total angular momentum of a closed system remains constant. Angular momentum has both a direction and a magnitude, and both are conserved. Bicycles and motorcycles, flying discs, rifled bullets, and gyroscopes owe their useful properties to conservation of angular momentum.

Related lectures (50)

Gradient Descent

Covers the concept of gradient descent in scalar cases, focusing on finding the minimum of a function by iteratively moving in the direction of the negative gradient.

Perception: Data-Driven Approaches

Explores perception in deep learning for autonomous vehicles, covering image classification, optimization methods, and the role of representation in machine learning.

Multilayer Perceptron: Training and Optimization

Explores the multilayer perceptron model, training, optimization, data preprocessing, activation functions, backpropagation, and regularization.

Conservation Laws: Properties and Known Laws

Covers the definition of conservation laws and known laws related to momentum, energy, and helicity.

Optimization Methods: RMSprop and ADAM