第 8 / 17 页
非代码面试题
显示 20 / 333 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
2464No Test Labels Touched Is Not EnoughSomeone argues there was no leakage because the code never accessed test labels. Give the core reason this defense can fail in real ML pipelines.机器学习困难essay未尝试面试订阅2471Slope From Centered Sufficient Statistics 1In simple OLS with an intercept, if the centered sufficient statistics satisfy sum i (x i-xbar)(y i-ybar)=S xy and sum i (x i-xbar) 2=S xx, derive beta hat.机器学习简单derivation未尝试免费2473Scaling One Feature Rescales Its Coefficient 3If a feature x is replaced by x new = c x in an OLS model with an intercept, how does its fitted coefficient change when all fitted values are kept identical?机器学习中等derivation未尝试面试订阅2474Shifting the Response by a Constant 4If every target value is replaced by y i + k in an OLS model with an intercept, what happens to the fitted slope and intercept?机器学习中等derivation未尝试面试订阅2478Residual Orthogonality to Features 8Why must the OLS residual vector be orthogonal to every column of the design matrix at the optimum?机器学习中等derivation未尝试面试订阅2479Why Multicollinearity Hurts Coefficient Stability More Than Fit 10Why can severe multicollinearity make coefficients unstable even when training predictions barely change?机器学习中等essay未尝试面试订阅2485Why Gradient Descent and Closed Form Agree 15Why do exact gradient descent convergence and the normal-equation solution agree for OLS?机器学习困难derivation未尝试面试订阅2488Why Residual Mean Is Zero With an Intercept 18Why must OLS residuals sum to zero whenever an intercept is included?机器学习困难derivation未尝试面试订阅2489A Constant Shift in One Feature 19If a feature x is replaced by x+k in a regression that already includes an intercept, what happens to the slope on x and the intercept?机器学习中等derivation未尝试面试订阅2495When OLS Predictions Are Unique 25Even if the coefficient vector is not unique, why is the OLS fitted prediction X beta hat still unique?机器学习困难derivation未尝试面试订阅2498Lasso Zero Threshold in an Orthogonal Coordinate 3In an orthogonal one-feature problem with x T x = d and score z = x T y, for what lambdas does the lasso coefficient become exactly zero?机器学习中等derivation未尝试免费2502Elastic-Net Coordinate Update in an Orthogonal Basis 7In an orthogonal coordinate with x T x = d and score z, derive the elastic-net coefficient with L1 weight lambda 1 and L2 weight lambda 2 when the coefficient is active and positive.机器学习简单derivation未尝试免费2511Why L1 Produces Corners and Corners Produce Sparsity 11Why is the geometry of the L1 ball often used to explain why lasso creates sparse solutions?机器学习简单essay未尝试免费2513Why Correlated Features Frustrate Pure Lasso 17Why does pure lasso often behave erratically when several features are highly correlated and similarly predictive?机器学习中等essay未尝试面试订阅2518Ridge Shrinkage Ratio Numerically 23In an orthogonal coordinate with d = 6 and lambda = 2, what fraction of the OLS coefficient remains under ridge?机器学习中等derivation未尝试面试订阅2537Why Logistic Probabilities Are Useful Downstream 18Why is it valuable that logistic regression produces a calibrated probability estimate rather than only a hard class label?机器学习中等essay未尝试面试订阅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2540Intercept Shift for a Deployment Prior ChangeA logistic model was trained under class prior 0.5 and has intercept -0.4. At deployment the base rate falls to 0.2 while feature likelihood ratios are assumed unchanged. What adjusted intercept should be used?机器学习困难数值题未尝试面试订阅2554Cost-Sensitive Leaf Label 21A leaf contains 7 positives and 13 negatives. Predicting negative incurs false-negative cost 4 on each hidden positive, while predicting positive incurs false-positive cost 1 on each hidden negative. Which class should the leaf predict?机器学习中等数值题未尝试面试订阅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