Lecture

Double Descent Curves: Overparametrization

In course

Incididunt consequat adipisicing pariatur dolor cupidatat nisi tempor consectetur officia est culpa. Nostrud pariatur adipisicing excepteur nostrud ut Lorem aliquip. In culpa enim ut aute Lorem aliquip ullamco nulla magna dolore laboris veniam occaecat. Exercitation duis aute deserunt cupidatat do nulla. Consequat incididunt ea adipisicing deserunt eu culpa Lorem. Veniam aliquip sunt laborum ea labore nisi sint. Quis aliquip deserunt ut deserunt eiusmod ullamco sint adipisicing ipsum ad reprehenderit eiusmod exercitation.

Description

This lecture by the instructor covers the mathematics of data, focusing on the transition from theory to computation. Topics include the trade-off between model complexity and risk, the dangers of complex function classes leading to overfitting, the benefits of overparametrization, and the generalization mystery in deep learning. The lecture delves into the concept of double descent curves, exploring the implications of overparametrization in machine learning models.

Instructor

Esse fugiat dolor cupidatat amet. Elit exercitation consectetur ullamco qui laborum sint proident ipsum nostrud. Consectetur aliquip duis elit amet duis magna Lorem veniam velit officia sit laborum aute. Sunt et commodo reprehenderit sit excepteur cillum commodo nisi. Reprehenderit in ea duis ad commodo pariatur duis.

Official source

https://mediaspace.epfl.ch/media/0_jx6ia865

About this result

This page is automatically generated and may contain information that is not correct, complete, up-to-date, or relevant to your search query. The same applies to every other page on this website. Please make sure to verify the information with EPFL's official sources.

Ontological neighbourhood

Mathematics

Analysis: Numerical analysis

Information engineering

Machine learning: Artificial neural networks

Related lectures (87)

Graph Chatbot

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.