You are training a spam classifier and observe overfitting. Which three actions will help reduce overfitting? (Choose three.)

Overfitting occurs when a model learns the training data too well, including noise, and performs poorly on unseen data. Getting more training examples helps the model learn the underlying patterns rather than memorizing noise. Using a smaller set of features (feature selection) reduces model complexity, making it less likely to fit noise in high-dimensional data. Increasing the regularization parameter(s) penalizes large coefficients, discouraging complex models and promoting simpler, more generalizable solutions. Reducing the number of training examples would exacerbate overfitting. Using a larger set of features would increase model complexity and the risk of overfitting. Decreasing the regularization parameter(s) would reduce the penalty on complexity, making overfitting more likely.