第 5 / 9 页
非代码面试题
显示 20 / 171 道匹配题目
答题状态：未尝试未正确已正确
ID题目领域难度题型进度权限
2528Why Log-Loss Rewards Calibration 9Why does a well-calibrated probability forecaster typically fare better under log-loss than a forecaster that only gets rankings right?机器学习中等essay未尝试免费2538Why Logistic Beats Hard Threshold Rules for Training 23Why is a smooth probabilistic loss easier to optimize than training directly against a hard classification rule?机器学习中等essay未尝试免费2552Which Split Becomes Best After a Perturbation 19Split A originally has gain 1.20 and split B has gain 1.05. After one row is corrected, A loses 0.10 gain while B gains 0.08. Which split is now best?机器学习中等数值题未尝试免费2559Expected Misroutes From a Surrogate SplitA surrogate split agrees with the primary split on 34 of 40 training cases where both features are present. If 12 production cases are missing the primary split feature and are routed by the surrogate, what is the expected number of misroutes?机器学习困难derivation未尝试面试订阅2564Validation Penalty Threshold for Keeping a SplitA stump has validation loss 30. Splitting it into two leaves lowers validation loss to 22 but adds an instability penalty lambda per extra leaf. For what largest lambda is the split still preferred?机器学习困难derivation未尝试面试订阅2567Why Two Nearly-Tied First Splits Can Diverge Later 13Why can two root splits with almost identical immediate gain still lead to very different final trees?机器学习简单essay未尝试免费2569Why Axis-Aligned Trees Struggle on Rotated Boundaries 14Why can a decision tree need many small rectangles to approximate a simple diagonal boundary?机器学习中等essay未尝试面试订阅2571Variance of an Average of Correlated Trees 1Suppose B trees each have variance sigma 2 and every pair has correlation rho. Derive the variance of their simple average.机器学习简单derivation未尝试免费2573Infinite-Forest Variance Floor 2Using the equicorrelated-tree variance formula, derive the prediction variance as the number of trees B tends to infinity.机器学习中等derivation未尝试免费2575Why Bagging Rarely Fixes High Bias 11Why should you not expect bagging alone to rescue a learner whose individual trees are systematically misspecified?机器学习困难essay未尝试面试订阅2576Why Feature Subsampling Helps When One Predictor Dominates 12Why can random feature subsampling improve a forest when one very strong predictor would otherwise appear at the top of almost every tree?机器学习简单essay未尝试免费2578Why Tiny max_features Can Raise Bias 14Why can making max features too small hurt a random forest even though it lowers correlation?机器学习中等essay未尝试免费2579Infer Tree Correlation From the Variance Floor 23A single tree has variance 6, while an extremely large forest appears to level off at variance 1.8. What pairwise tree correlation rho is implied?机器学习中等数值题未尝试面试订阅2580Why More Trees Usually Do Not Create Classical Overfit 15Why does adding more trees to a random forest typically plateau rather than create the kind of explosive overfit seen in some single-model families?机器学习困难essay未尝试面试订阅2584Marginal Variance Reduction From One More Tree 3Under the equicorrelated-tree model, derive how much the ensemble variance falls when you move from B trees to B+1 trees.机器学习困难derivation未尝试面试订阅2585Trees Needed for a Target Variance Cap 4Suppose each tree has variance sigma 2 and pairwise correlation rho. Derive the minimum B needed to make the ensemble variance at most V, assuming V > rho sigma 2.机器学习困难derivation未尝试面试订阅2591Why OOB Can Be Noisy on Small Samples 19Why can out-of-bag error fluctuate a lot on a small dataset even when the forest itself is reasonably stable?机器学习简单essay未尝试免费2592Effective Independent Tree Count 8Define B eff by matching the correlated-forest variance sigma 2 [rho + (1-rho)/B] to the variance sigma 2 / B eff of averaging independent trees. Derive B eff.机器学习简单derivation未尝试免费2593Why Averaging Cannot Cure Systematic Label Noise 20Why can a larger forest fail to repair performance when the training labels themselves are systematically corrupted?机器学习中等essay未尝试面试订阅2599Why Boosting Mostly Attacks Bias 9Why is boosting usually described as a bias-reduction method more than a variance-reduction method?机器学习中等essay未尝试免费