-
Hi, I am curious if the framework supports calculating the L2 local Lipschitz constant (bound of the L2-norm of the Jacobian).
The NeurIPS 2022 paper seems like it is suggesting that only L-inf norm …
-
When we use step_size=1/Lipschitz constant, and the CIL norm underestimates the norm, this leads to a larger step size and could cause issues with convergence.
Something to discuss with @epapoutse…
-
There has been several requests for group lasso regularised Poisson regression. This was more difficult than first thought as the gradient of the Poisson loss is not globally Lipschitz.
The loss gr…
-
It is often of interest to find the nonlinear operator norm, and this is especially relevant for things like:
```
odl.diagnostics.OperatorTest(op).derivative()
```
which currently throws an error if…
-
Hi,
I am wondering if it is possible to apply your method to a single layer, i.e., **relu(Wx + b)**. When I try to give LipSDP one layer, I get an "Inner matrix dimensions must agree." error. More …
-
In Accessors v0.1.5.
Breaks down when the type parameter is not "used" in the struct.
```julia
julia> using Accessors
julia> struct MyType{T}
i::Int64
end
julia> m = M…
-
@takerum
I have a question about a batch normalization layer with the spectral normlization.
The following discussion ignores biases parameters as they do not affect the Lipschitz constant.
Gene…
-
LOBPCG variants were merged in https://github.com/pytorch/pytorch/pull/29488
However, spectral_norm [implementation](https://github.com/pytorch/pytorch/blob/master/torch/nn/utils/spectral_norm.py#L…
-
We want to be able to do completely random mini-batch stochastic gradient descent ( or maybe other flavours...)
We could consider something like:
https://github.com/epapoutsellis/StochasticCIL/bl…
-
After seeing [Issue #114](https://github.com/MagneticResonanceImaging/MRIReco.jl/issues/114#issue-1397838023) on MRIReco.jl, I noticed that certain algorithms (e.g. ADMM) scale the data fidelity term …