Miguel de Benito Delgado
Miguel de Benito Delgado
I think it is worthwhile mentioning the setup and logic behind it in the contributing document.
* [ ] Make Scorer accept tensors and return tensors (e.g. to allow returning the model parameters) * [ ] Constructing from strings should be a factory
As described in 4.3 of _Jia, Ruoxi, David Dao, Boxin Wang, Frances Ann Hubis, Nick Hynes, Nezihe Merve Gürel, Bo Li, Ce Zhang, Dawn Song, and Costas J. Spanos. ‘Towards...
_Wang, Tianhao, Yu Yang, and Ruoxi Jia. “Improving Cooperative Game Theory-Based Data Valuation via Data Utility Learning.” arXiv, 2022. https://doi.org/10.48550/arXiv.2107.06336._ - [x] #157 - [x] #138 - [ ] Run...
As part of the preparation for #282 and #123 or #279, `Dataset` should work with one type (possibly a protocol implementing `.shape` and indexing and little more) which encompasses tensors...
- [ ] Statistics like total time, average time between single updates (should be optional) - [ ] `StoppingCriterion` that updates the status (could be logical or/and) - [ ]...
As introduced in _Simon, Grah, and Thouvenot Vincent. ‘A Projected Stochastic Gradient Algorithm for Estimating Shapley Value Applied in Attribute Importance’. In Machine Learning and Knowledge Extraction, edited by Andreas...
_Jia, Ruoxi, David Dao, Boxin Wang, Frances Ann Hubis, Nick Hynes, Nezihe Merve Gürel, Bo Li, Ce Zhang, Dawn Song, and Costas J. Spanos. ‘Towards Efficient Data Valuation Based on...
As described in 4.5 of _Jia, Ruoxi, David Dao, Boxin Wang, Frances Ann Hubis, Nick Hynes, Nezihe Merve Gürel, Bo Li, Ce Zhang, Dawn Song, and Costas J. Spanos. ‘Towards...
The standard (ε,δ)-bound for the MonteCarlo SV approximation assumes a deterministic utility, but one never has this. Instead: make an additional (ε,δ)-assumption on the utility and nest the bounds. However,...