Comments (2)
I think the more useful result is to pick a something like a sub-gradient. The use case to imagine is some optimisation problem, where equality might be the best or worst point. We'd like gradient descent to be able to end up there, or not to get stuck there, both of which want a finite gradient.
You could argue that these should pick a symmetric convention, though:
julia> ForwardDiff.gradient(x -> max(x...), [1,1])
2-element Vector{Int64}:
0
1
julia> ForwardDiff.derivative(x -> clamp(x, 1, 2), 1)
1
julia> ForwardDiff.derivative(x -> clamp(x, 1, 2), 2)
1
from diffrules.jl.
Yes, the problem I had was encountered when optimizing a function with max(x, y)
inside it. I was checking the gradients using ForwardDiff
and realized that problem of no symmetry. Worse, though, is FiniteDiff
:
julia> FiniteDiff.finite_difference_gradient(x -> max(x...), [1.0, 1.0])
2-element Vector{Float64}:
0.4999999999934427
0.4999999999934427
from diffrules.jl.
Related Issues (20)
- rule for tanh has catastrophic cancellation for |x| > 20 HOT 2
- Stable documentat is not latest
- clarify @define_diffrule namespaces HOT 4
- Scalar DiffRules which use the output HOT 1
- Package compatibility caps
- no type annotations HOT 1
- Cannot backprop `x^a` when `x` is negative HOT 2
- diffrule for fma HOT 1
- Lack rule for Base.log with 2 arguments which is overloaded
- Release a major? HOT 5
- Lack rule for `ifelse` HOT 5
- TagBot trigger issue HOT 32
- rule for GSL functions HOT 1
- Rule for `SpecialFunctions.beta_inc` HOT 1
- Version info is confusing HOT 2
- closed under packages? HOT 1
- missing `logabsgamma` rules HOT 7
- Type instability in ldexp with Float32 arguments HOT 1
- Problems with the `DEFINED_DIFFRULES` implementation
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 diffrules.jl.