Joff's user avatar
Joff's user avatar
Joff's user avatar
Joff
  • Member for 3 years, 4 months
  • Last seen this week
15 votes
1 answer
775 views

How to determine if a sample is within a standard deviation of a multivariate normal distribution

7 votes
3 answers
803 views

What does it mean that a Gaussian process is 'infinite dimensional?'

5 votes
1 answer
148 views

Gradient of the log likelihood for energy based models

3 votes
1 answer
367 views

Cholesky decomposition lower triangular in Gaussian process sampling

3 votes
1 answer
61 views

How does the approximate Hessian update in LBFGS work?

3 votes
1 answer
45 views

How to know the number of dimensions of a Jacobian?

3 votes
2 answers
128 views

Does the Bernstein von Mises theorem require that the true posterior is actually Gaussian?

2 votes
0 answers
266 views

Pyro Gaussian processes regression achieves a low error, but then always outputs the same prediction on new data

2 votes
1 answer
118 views

Is negative log likelihood calculated in log space or exponential space?

1 vote
1 answer
1k views

What is the Hessian of the Gaussian likelihood

1 vote
0 answers
162 views

Random Fourier Features approximating a kernel inverse?

1 vote
0 answers
37 views

effect of multiplying by Tikhonov regularization factor after an inverse?

1 vote
1 answer
109 views

Does centering data destroy information if the data are not gaussian distributed?

1 vote
0 answers
41 views

How to calculate log likelihood for a model which outputs log probability?

1 vote
1 answer
276 views

What is the difference between a covariance matrix created by an RBF kernel and a covariance matrix created by

1 vote
1 answer
88 views

Can any covariance factorization $LL^\top$ be used for sampling?

1 vote
0 answers
15 views

A question about linear inference in random Fourier feature kernels

1 vote
0 answers
9 views

How does the fixed point interation in invertible resnets work?

0 votes
0 answers
15 views

Why is the cholesky decomposition the correct matrix square root to sample from? [duplicate]

0 votes
0 answers
119 views

Why is the Hessian in the Laplace approximation negative

0 votes
0 answers
132 views

When is a high learning rate for Stochastic Gradient Descent a good thing?

0 votes
0 answers
18 views

What is the significance of a high value of $x^\top A^{-1} x$ as it relates to Gaussian processes

0 votes
1 answer
44 views

Can someone explain Stein's method/discrepancy in a way that makes sense?

0 votes
0 answers
30 views

Is negative Mahalanobis distance proportional to log probability?