À suivreGuide suivant
Décodage minimum du risque Bayesien
IA linguistique
GUIDE des fondamentaux
Empirical Risk Minimization
Empirical risk minimization (ERM) chooses a hypothesis by minimizing its average loss on a finite training sample as a proxy for expected loss under an unknown data distribution.
Sur cette page3 minutes de lecture
Aperçu
It matters because fit to that sample can differ from performance on new data, which is why model complexity and independent evaluation are part of the learning problem.
Plongée profonde
Empirical risk minimization formalizes what most machine learning training actually does. The true risk of a model is the expected value of some loss function over the entire, usually infinite and unknown, distribution of possible data. Since that distribution is inaccessible, ERM substitutes it with the empirical risk: the average loss computed over a finite training sample drawn from that distribution. Learning becomes an optimization problem: search over a hypothesis class (all linear functions, or all neural networks of a given architecture) for the one that minimizes this average sample loss, typically via gradient descent or a closed-form solution. For a fixed hypothesis and representative independent samples, average sample loss can estimate expected loss. To make a guarantee that holds across a whole hypothesis class, additional conditions on the class and sample are needed; uniform-convergence results such as VC bounds make those assumptions explicit. The catch is that minimizing training loss too aggressively, especially with a hypothesis class that is complex relative to the sample size, can drive empirical risk toward zero while true risk stays high; the model has memorized noise specific to the training sample rather than learning the underlying pattern. This is overfitting, and it is why practitioners use regularization, cross-validation, and held-out test sets: not because ERM is wrong, but because minimizing empirical risk alone provides no guarantee about true risk without additional constraints or enough data relative to model complexity. A common misconception is that ERM refers to a specific algorithm; it is a general principle that many learning procedures use, sometimes with regularization or other constraints and different loss functions or hypothesis classes.
Impact stratégique
Décisions plus claires
Il vous aide à séparer les affirmations techniques claires du langage marketing.
Coût et budget
Vous pouvez poser de meilleures questions de mise en œuvre avant de dépenser de l'argent ou du temps.
Équipe et flux de travail
Les équipes partageant une compréhension commune prennent de meilleures décisions en matière de produits, de politiques et d’apprentissage.
The Future of Empirical Risk Minimization
ERM remains a widely used training principle across supervised learning, often combined with regularization or other constraints, from simple regressions to large neural networks, and this is unlikely to change since it is a general mathematical framework rather than a specific technique that could be superseded. Active research continues on refining the gap between empirical and true risk for very large, over-parameterized models, where classical overfitting intuitions sometimes fail to predict observed generalization behavior. Work on distributionally robust optimization and other risk formulations extends ERM's ideas to handle shifts between training and deployment data, but these remain extensions of the same underlying principle.
Mise en œuvre dans le monde réel
Training a spam filter by adjusting its parameters to minimize the fraction of misclassified emails in a labeled training set, hoping this generalizes to new incoming email.
Fitting a linear regression line by minimizing mean squared error across the observed data points, which is literally ERM with squared-error loss.
A neural network's training loop that repeatedly computes gradient updates to reduce average cross-entropy loss over mini-batches drawn from the training set.
A model that achieves near-zero error on training data but performs poorly on new data, illustrating the gap between empirical risk (training loss) and true risk (expected loss on unseen data), i.e. overfitting.
Risques et garde-fous
Différentes équipes peuvent utiliser le même terme différemment, alors définissez la portée dès le début.
Les benchmarks peuvent paraître solides alors que les performances réelles sont inégales.
Ignorer la qualité des données et les plans d’évaluation crée souvent des résultats fragiles.
Feuille de route de mise en œuvre
Commencez par une définition en langage simple du résultat dont vous avez besoin.
Choisissez une mesure de réussite et une condition d’échec avant de tester.
Exécutez un petit pilote avec des données représentatives, pas un ensemble de démonstration raffiné.
Document where Empirical Risk Minimization helps and where simpler methods are better.
Continuez à explorer
Free newsletter
Get the daily AI briefing
Three verified AI stories every weekday morning, written in plain English. Free forever, no ads.
One email each weekday. Unsubscribe in one click. We never sell or share your address.
Test yourself
Take the Empirical Risk Minimization quiz
Instant feedback on every answer, and a shareable certificate with a verifiable ID once you pass a course.
Support free AI education. AI Understanding is a 501(c)(3) nonprofit — no ads, no paywall, ever. Make a donation
Questions fréquemment posées
What is Empirical Risk Minimization?
Empirical risk minimization (ERM) chooses a hypothesis by minimizing its average loss on a finite training sample as a proxy for expected loss under an unknown data distribution. It matters because fit to that sample can differ from performance on new data, which is why model complexity and independent evaluation are part of the learning problem.
What does empirical risk minimization actually minimize during training?
ERM substitutes the unobservable true risk with the empirical risk, the average loss measured on the finite training sample actually available.
Why can't a model directly minimize true risk instead of empirical risk?
True risk is an expectation over the full, typically unknown and infinite data distribution, so it cannot be computed directly; only a finite sample is available.
As an IID sample grows, what classical result helps explain why its average loss can estimate expected loss for a fixed model?
The guide cites the law of large numbers and VC-theory uniform convergence bounds as the theoretical basis for empirical risk converging to true risk with more data.
During training, what does overfitting look like when empirical and true risk are compared?
Overfitting occurs when a model memorizes training-sample-specific noise, achieving very low empirical risk while its true risk on unseen data stays high.
What role does regularization play in the ERM objective?
Regularization adds a penalty, such as an L2 norm term, to the ERM objective, accepting somewhat higher training loss in exchange for a hypothesis that generalizes better.
Continuez à apprendre
Guides associés
Plus de guides sélectionnés pour ce sujet