Comments (3)
So after thinking about this for a bit (I actually discovered it yesterday), and drawing on a little bit of experience from JuliaDiff/ForwardDiff.jl#83, I think the safest and most tenable approach is to simply not apply the unsafe optimizations by default, and instead provide users an @optdiff
macro (or something) which can be used to assert that it is safe to perform an AD optimization based on context.
Note that it really would have to be an unchecked user-assertion; I don't think you can adequately check for function purity at macro-time (well, maybe you could, but it would probably be really messy/fragile). If Julia ever gets better support for introspecting function purity (an ispure
trait or something), we might enable the optimization for pure functions automatically.
Anyway, requiring a directive isn't the most elegant solution, but it would at least solve the problem and still allow users to access the optimization.
from reversediff.jl.
What are the unsafe optimizations?
from reversediff.jl.
What are the unsafe optimizations?
See here.
We overload map
/broadcast
for AbstractArray{T <: TraceReal}
so that we can skip writing a bunch of nodes to the tape. Instead, we get the derivatives in the forward pass using arrays of Dual
s, and store the whole map
/broadcast
operation as a single "bulk" node (whose reverse pass behavior is defined here).
This optimization is unsafe if the function passed to map
/broadcast
closes over TraceReal
s, because those TraceReal
s will then unexpectedly write operations to the tape, where the optimization assumes that it's skipping though operations.
Unfortunately, like perturbation confusion, it's probably not transparent for a user to predict when this kind of thing will happen. It's also hard to detect automatically, so we can't reliably warn users either.
from reversediff.jl.
Related Issues (20)
- Error when using scalar vs. vector to operate on tracked inupt HOT 1
- Record `Broadcast.broadcasted` instead of `Broadcast.broadcast`
- MethodError: ReverseDiff.TrackedReal ... is ambiguous.
- double free crash with multi-threaded code only when using multiple threads
- @grad_from_chainrules macro fails when using multi-output functions HOT 2
- ReverseDiff documentation shows issue that has been fixed? Nested differentiation of a closure? HOT 1
- `MethodError: *(::Diagonal, ::ReverseDiff.TrackedArray)` is ambiguous.
- `@grad_from_chainrules` hygiene: cannot use custom types in method signature HOT 3
- Define `typemin` for tracked reals.
- ReverseDiff defines a huge number of methods. HOT 3
- Nested differentiation of closures yields incorrect results. Any news on the fix?
- Enhancement proposal: Modular tape caching HOT 16
- Bug: Derivative of transposed-vector times matrix is incorrect. HOT 5
- Strange bug when deferring to ChainRules HOT 1
- Add ChainRulesCore RuleConfig? HOT 1
- mean BigFloat precision
- MethodError: vcat(::ReverseDiff.TrackedArray{Float32, Float32, 2, Matrix{Float32}, Matrix{Float32}}, ::Matrix{Float32}) is ambiguous. HOT 4
- Method ambiguities reported by Aqua
- DiffResults objects are not re-aliased properly HOT 2
- ERROR: LoadError: Some tests did not pass: 146 passed, 0 failed, 1 errored, 0 broken. HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from reversediff.jl.