-
# Adding an optimization module
For now, Tensorly (TL) ships with one API for each particular tensor decomposition model. While this has the advantage of simplicity for the end-user, this limits the …
-
## Keyword: sgd
### A Convergence Theory for Federated Average: Beyond Smoothness
- **Authors:** Authors: Xiaoxiao Li, Zhao Song, Runzhou Tao, Guangyi Zhang
- **Subjects:** Machine Learning (cs.LG);…
-
I'm currently working on some updates to quasi-Newton direction update rules. Here are a few things to check/consider:
- [x] `QuasiNewtonCautiousDirectionUpdate` doesn't seem to use `θ` function anyw…
-
Hi,
Great work!
I have been studying the LPLR algorithm and I have a question regarding the computational complexity mentioned.
The paper states that the computational complexity of the LPLR al…
-
Under the "Restrictions" heading on the bottom of the minimize command manual entry (https://docs.lammps.org/minimize.html), there is a statement you'd be interested in implementing energy minimizatio…
-
I was about to start writing code, but I think it's worth having a discussion first. If we're going to realize my eventual vision of autonomous creation of valid "directed graphs of transformations",…
-
Is there any interest in adding a quasi-Newton based optimizer? I was thinking of porting over:
https://github.com/tensorflow/probability/blob/master/tensorflow_probability/python/optimizer/bfgs.py…
-
function [tx,F,H,G,flag,k,P,NLL] = cbm_optim(h,optconfig,rng,numrep,init0,fid)
% This function minimizes h using the fminunc routine in matlab (with
% matlab versions after 2013a).
%
% copied fr…
-
Creating a big ticket using the list from/for the paper, closing smaller issues.
Ultimately, this should be closed in favour of much more specific tickets ("implement method x")
# Optimisers
…
-
So in the documentation there is the sentence:
> An AbstractGP, f, should be thought of as a distribution over functions. This means that the output of rand(f) would be a real-valued function. It's…