Questions


The Infinite Gaussian Mixture Model (5)
pm.Categorical behaves differently in a model versus as pm.Categorical.dist (3)
Sampling from prior predictive distribution (13)
A question about the scope of the variable (5)
Multivariatre categorical variable with different values (4)
Metropolis equivalent to NUTS target_accept? (4)
Normal distribution throws errors when using shared variables (4)
Semi-open uniform distribution (2)
How to save fitted ADVI Result? (4)
Weird posterior for correlation structure using LKJ distribution (6)
Sum of random variables? (3)
Very slow generation of computation graph with convolution (1)
How does sampling effect the logp? (3)
Issue using pm.Interpolated() to update priors in online updating loop (2)
Softmax regression. Theano `softmax` function slow? (1)
Error when I build a new program by pymc3 (3)
Error while using DensityDist (2)
Evaluating Variational Inference: Need Access to fitted (AD)VI approximation density (3)
Likelihood given by product of two distributions? (7)
Multidimensional indexing (9)
Positive samples (2)
NUTS - FromFunctionOp has no attribute 'grad' (3)
Model with extended likelihood function using pm.DensityDist or pm.Potential (5)
Probabilistic Programming vs Probabilistic Graphical Models (2)
LDA implementation with pymc3 (20)
Memory problems with nested theano.scan (2)
"ValueError: Bad initial energy: inf. The model might be misspecified" (3)
ValueError: design matrix must be real-valued floating point (11)
Model yeilding no samples (2)
A newbie question: How should I formulate a classification problem using PyMC3? (6)