- Help with recreation of table
- How do I open PDF in Adobe Reader DC without locking the file from being updated by pdflatex?
- How do I allow floats to appear before being refered to? (two column)
- joining two points on an arc
- Cross-referencing pictures - show picture not its caption
- Bizarre \hline behaviour in tabular environment
- How to use alphaurl as bibliography style?
- Modification of a template
- How can we remove/delete content outside PDF/EPS bounding box?
- Error while using Watershed tool
- Overlapping features and attributes help
- Cogo tool inputs differ from survey plan needing digitization
- Selecting point to obtain watershed leading to it
- rgdal loads PROJ.4 version 4.9.1 when the updated 4.9.2 is installed
- Removing small areas from raster layer using QGIS?
- Automatically assigning current map scale to shape created in QGIS?
- Problems installing QGIS 2.14.14 nor QGIS 2.18.6 (32-bit) on my Windows Vista 32-bit computer
- cannot click on points in openlayers
- A simple label for an entire MapServer mapfile?
- error while running las dataset to raster function
Deep Learning: What are the differences between DeepMind's Learning to Learn method and a grid search of a network's hyperparameters?
If we have a meta-learner that trains an optimizer (who contains certain hyperparameters) and the optimizer is fine-tuned by the meta-learner depending on how it performs, how is it different from a usual grid search of the best hyperparameters? One way I think it's different is that the meta-learner can supposedly 'intelligently' find the best optimizer but a gridsearch is rather a brute-force method. But a grid search would likely include human knowledge on the range of hyperparameters where the model is likely to perform well.
My current impression is that the meta-learner simply tweaks the hyperparameters of the optimizer (which are usually fixed in many other cases) after certain number of epochs, evaluates the performance, then dynamically changes how the hyperparameters should be tweaked. Is this what the authors of the paper did?