Lecture

Generalization and Overfitting

Graph Chat

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.

In course

EE-311: Fundamentals of machine learning

Ce cours présente une vue générale des techniques d'apprentissage automatique, passant en revue les algorithmes, le formalisme théorique et les protocoles expérimentaux. ...

Description

This lecture discusses the concepts of generalization and overfitting in machine learning models. Generalization refers to a model's ability to make accurate predictions on new, unseen data. Overfitting occurs when a model is too complex and captures noise in the training data, leading to poor performance on new data. Underfitting, on the other hand, happens when a model is too simple and fails to capture the underlying patterns in the data. The lecture illustrates these concepts with examples of models of varying complexity and the trade-off between the number of parameters and the amount of training data. It also covers different loss functions for model evaluation and the importance of considering outliers in the data. The goal is to find a balance between model complexity and data availability to achieve optimal performance.

Instructors (2)

François Fleuret

Michael Stefan Daniel Liebling

Teaching & PhD Past EPFL PhD Students as codirector Christian Jaques, Olivia Mariani, Adrian Shajkofci, François Thierry M Marelli Courses Fundamentals of machine learning EE-311 This course provides a general overview of machine learning, covering the main algorithms, theoretical formalisms, and experimental protocols.

Official source

Related concepts (31)

Generalization error

For supervised learning applications in machine learning and statistical learning theory, generalization error (also known as the out-of-sample error or the risk) is a measure of how accurately an algorithm is able to predict outcome values for previously unseen data. Because learning algorithms are evaluated on finite samples, the evaluation of a learning algorithm may be sensitive to sampling error. As a result, measurements of prediction error on the current data may not provide much information about predictive ability on new data.

Bias–variance tradeoff

In statistics and machine learning, the bias–variance tradeoff is the property of a model that the variance of the parameter estimated across samples can be reduced by increasing the bias in the estimated parameters. The bias–variance dilemma or bias–variance problem is the conflict in trying to simultaneously minimize these two sources of error that prevent supervised learning algorithms from generalizing beyond their training set: The bias error is an error from erroneous assumptions in the learning algorithm.

Regularization (mathematics)

In mathematics, statistics, finance, computer science, particularly in machine learning and inverse problems, regularization is a process that changes the result answer to be "simpler". It is often used to obtain results for ill-posed problems or to prevent overfitting. Although regularization procedures can be divided in many ways, the following delineation is particularly helpful: Explicit regularization is regularization whenever one explicitly adds a term to the optimization problem.

Akaike information criterion

The Akaike information criterion (AIC) is an estimator of prediction error and thereby relative quality of statistical models for a given set of data. Given a collection of models for the data, AIC estimates the quality of each model, relative to each of the other models. Thus, AIC provides a means for model selection. AIC is founded on information theory. When a statistical model is used to represent the process that generated the data, the representation will almost never be exact; so some information will be lost by using the model to represent the process.

Computational complexity

In computer science, the computational complexity or simply complexity of an algorithm is the amount of resources required to run it. Particular focus is given to computation time (generally measured by the number of needed elementary operations) and memory storage requirements. The complexity of a problem is the complexity of the best algorithms that allow solving the problem. The study of the complexity of explicitly given algorithms is called analysis of algorithms, while the study of the complexity of problems is called computational complexity theory.

Related lectures (64)

Overfitting vs Underfitting MOOC: IoT Systems and Industrial Applications with Design Thinking

Explores the impact of model complexity on error rates in machine learning.

Generalization Theory

Explores generalization theory in machine learning, addressing challenges in higher-dimensional spaces and the bias-variance tradeoff.

Model Assessment and Hyperparameter Tuning

Explores model assessment, hyperparameter tuning, and resampling strategies in machine learning.

Machine Learning Fundamentals: Overfitting and Regularization

Covers overfitting, regularization, and cross-validation in machine learning, exploring polynomial curve fitting, feature expansion, kernel functions, and model selection.

Decision Trees and Random Forests: Concepts and Applications