-
I've run into an issue with large matrices and memory. There seem to be two problems:
1) Memory isn't being released on successive calls of grad. e.g.
```
a = 10000
b = 10000
A = np.random.randn(a)
…
-
These new constructors will sit on top of the existing lower-level parameter-related constructors to enable optional computation of target derivatives via AD.
-
Dynd is a next generation array library for python, with lots of cool features like JIT compilation, heterogenous data, user defined data types, missing data support, type checking etc https://speaker…
-
I am exploring using eval_grad_f to perform coordinate ascent steps in mean field variational models. At each step, I only need a few terms of the gradient, but eval_grad_f always returns the whole t…
-
I think it would be great if all the ODE/DAE solvers could be called through the same interface. This would essentially mirror the approach of https://github.com/JuliaOpt/MathProgBase.jl . Would it …
-
From Ben Goodrich on stan-dev:
It is kind of like the ODE thing but going the other way. In the case of a copula, we know the explicit form of the multivariate CDF of the marginal uniforms
```
F(u_1…
-
As of Stan 2.4, the code in `agrad/fwd` has dependencies into `agrad/rev` and the finite diff code is spread all over.
What I propose is creating four directories under agrad:
- `finite-diff`: for f…
-
The meta/traits.hpp file brings in agrad::var and agrad::fvar, which tangles up our math lib with our autodiff lib.
Dependencies should go only one way, from stan::agrad to stan::math, not vice-ver…
-
## Current Code Features
I see five cross-cutting ways our math and autodiff code can be categorized:
#### Type
- primitive
- reverse mode autodiff
- forward mode autodiff
- mixed mode autodiff
#### …
-
To what extent is it possible for automatic differentiation to tell us when the partial derivative of a function with respect to one of its inputs is everywhere zero?
The general approach works by ev…