User Siddharth Shakya

10 votes

1 answer

5k views

Why is lasso more robust to outliers compared to ridge?

asked Apr 22, 2019 at 22:39

8 votes

2 answers

904 views

Why is selection of one amongst the group of highly correlated variables by lasso is stated as its disadvantage?

asked May 21, 2017 at 16:43

6 votes

1 answer

4k views

What is the mathematical rigorous proof that L1 regularization will give sparse solution? [duplicate]

asked May 21, 2017 at 12:33

6 votes

1 answer

624 views

Machine learning algorithms as matrix factorization

asked Dec 18, 2017 at 9:35

5 votes

2 answers

1k views

Why are coefficient in regression model interpreted as change in response with unit increase in that variable with others constant?

asked Jun 5, 2017 at 12:59

5 votes

0 answers

671 views

What is the relation between stationary distribution, limiting distribution, ergodicity and detailed balance equation in a markov chain?

asked Aug 27, 2018 at 15:28

4 votes

2 answers

2k views

What happens if A is not invertible in equation Ax=b?

asked May 15, 2018 at 15:08

3 votes

1 answer

59 views

Would it be wrong if I use lasso in the following way?

asked Apr 3, 2018 at 6:20

3 votes

2 answers

763 views

Mutual exclusive classes for deciding Softmax Regression vs. k Binary Classifiers

asked Dec 22, 2017 at 17:20

3 votes

1 answer

830 views

Should the resulting weight vector of SVM be of unit length?

asked May 14, 2017 at 9:42

2 votes

1 answer

215 views

Can we always treat multiple output regression as separate regressions?

asked Nov 3, 2017 at 7:01

2 votes

1 answer

132 views

Why do we need Lack of Fit F-test?

asked Jan 26, 2018 at 9:43

2 votes

2 answers

4k views

What is K means objective function?

asked Jun 4, 2018 at 13:16

2 votes

1 answer

132 views

Why is Bayesian data analysis done if we already know the distribution of the parameters?

asked Jun 22, 2018 at 10:14

1 vote

0 answers

52 views

Is there any Good comprehensive reference for tensor calculus? [duplicate]

asked Sep 17, 2018 at 8:40

1 vote

1 answer

287 views

How does smoothing an image gives it a different scale?

asked Jan 9, 2019 at 8:42

1 vote

0 answers

52 views

Why can't we interpret likelihood as probability? [duplicate]

asked Jun 14, 2018 at 17:25

1 vote

0 answers

64 views

Using Chat-bots to understand API for speeding development process?

asked Mar 20, 2018 at 7:55

1 vote

0 answers

53 views

Is there a way to detect logical structure amongst text segments of technical documents?

asked Mar 29, 2018 at 16:00

1 vote

3 answers

608 views

How do to model selection and training?

asked Aug 27, 2017 at 10:01

1 vote

1 answer

3k views

Why is SVM sensitive to scaling of features? [duplicate]

asked May 16, 2017 at 13:17

1 vote

2 answers

232 views

Linear regression model is linear in inputs or linear in terms of its optimization function that is minimized to learn the weights?

asked May 24, 2017 at 6:10

0 votes

0 answers

37 views

Do we have any assumption on the distribution of Data for linear regression? [duplicate]

asked May 25, 2017 at 4:15

0 votes

1 answer

699 views

Which method to use for Initializing K means center? [duplicate]

asked Jun 6, 2018 at 15:35

Stack Exchange Network

24 Questions

Why is lasso more robust to outliers compared to ridge?

Why is selection of one amongst the group of highly correlated variables by lasso is stated as its disadvantage?

What is the mathematical rigorous proof that L1 regularization will give sparse solution? [duplicate]

Machine learning algorithms as matrix factorization

Why are coefficient in regression model interpreted as change in response with unit increase in that variable with others constant?

What is the relation between stationary distribution, limiting distribution, ergodicity and detailed balance equation in a markov chain?

What happens if A is not invertible in equation Ax=b?

Would it be wrong if I use lasso in the following way?

Mutual exclusive classes for deciding Softmax Regression vs. k Binary Classifiers

Should the resulting weight vector of SVM be of unit length?

Can we always treat multiple output regression as separate regressions?

Why do we need Lack of Fit F-test?

What is K means objective function?

Why is Bayesian data analysis done if we already know the distribution of the parameters?

Is there any Good comprehensive reference for tensor calculus? [duplicate]

How does smoothing an image gives it a different scale?

Why can't we interpret likelihood as probability? [duplicate]

Using Chat-bots to understand API for speeding development process?

Is there a way to detect logical structure amongst text segments of technical documents?

How do to model selection and training?

Why is SVM sensitive to scaling of features? [duplicate]

Linear regression model is linear in inputs or linear in terms of its optimization function that is minimized to learn the weights?

Do we have any assumption on the distribution of Data for linear regression? [duplicate]

Which method to use for Initializing K means center? [duplicate]