Kvíz spojený s průvodcem · Střední úroveň

Empirical Risk Minimization Quiz

Covers empirical versus true risk, sampling assumptions, overfitting, regularized objectives, and why held-out evaluation matters.

Související vodicí cestyEmpirical Risk Minimization
Otázka 1 z 8

What does empirical risk minimization actually minimize during training?

Náhled každé otázky8 otázky

Odpovědi a vysvětlení se zobrazují, jak budete v kvízu.

  1. What does empirical risk minimization actually minimize during training?
    • The true risk over the entire data distribution
    • Počet parametrů v modelu
    • The average loss computed over a finite training sample
    • The variance of the model's predictions
  2. Why can't a model directly minimize true risk instead of empirical risk?
    • True risk is defined over the entire, usually infinite and unknown data distribution, which is inaccessible
    • True risk is always higher so it's not worth minimizing
    • True risk cannot be expressed mathematically
    • Models are only capable of computing averages
  3. As an IID sample grows, what classical result helps explain why its average loss can estimate expected loss for a fixed model?
    • Bayesova věta
    • The central limit theorem alone
    • Newtonova metoda
    • The law of large numbers along with uniform convergence bounds from VC theory
  4. During training, what does overfitting look like when empirical and true risk are compared?
    • When both empirical and true risk are equally high
    • When empirical risk is driven low, even to zero, while true risk remains high
    • When a model refuses to train
    • When the hypothesis class is too small to fit any data
  5. What role does regularization play in the ERM objective?
    • It removes the loss function entirely
    • It guarantees zero true risk
    • It adds a penalty term that trades slightly higher empirical risk for a hypothesis less prone to overfitting
    • It only affects the learning rate
  6. Which of the following is explicitly given as an implementation of the general ERM principle?
    • Only neural networks
    • Only linear regression
    • None of these; ERM is a distinct algorithm separate from these
    • Linear regression, logistic regression, SVMs, and neural network training, each with different loss functions
  7. What does structural risk minimization add beyond basic regularized ERM?
    • It explicitly balances empirical risk against a measure of hypothesis-class complexity rather than fixing the class size
    • Odstraňuje potřebu ztrátové funkce
    • It guarantees the model will never overfit
    • It only applies to linear models
  8. In the ERM formula averaging L(h(x_i), y_i) over n examples, what does n represent?
    • The number of features in the model
    • Počet tréninkových příkladů
    • The number of hypothesis classes considered
    • Míra učení