General Experience

I spent these two weeks on conducting experiments, designing frameworks, and testing, iterating my algorithms. I have been mostly interested in comparing different algorithms and techniques. In addition, I made sure that the experimental results follow the mathematical formulas and observations I obtained earlier. It has been joyful and frustrating, exciting and boring! Good thing is that there were not any specific readings for these two weeks. I spent most of it reading threads on StackOverFlow and consulting github Discussion to resolve my code errors. My algorithm was mainly a domain generalization using causal and anticausal features through a set transformer, ending up with a model performing better than ERM done on a pooled dataset from multiple source and transfer domains. I ended up with a good start, but it is still needs a lot of modifications, refactoring, and editing.

Experiments and Results

My algorithm used a neural network with different layers, and the following were preliminary results.

This had a bug in it in the beginning, but I fixed the bug and this what I got This was a good start, but then it is still having an error term, where our model is approaching the pooled data. Therefore, next week I will be working on improving our model.

Frustrations

My main frustrations these past weeks were the bugs in my code, debugging and improving the results.

Plans for next week

The plan for next week is to improve the results. I will try adding a penalty or an regularization term. I will also start working on refactoring the code and testing it with different envrionment conditions.