Thanks for checking out my poster!
Links
👇 Learn More Below 👇
Overview
Black-box model access means we only know model inputs and model outputs. Using what we know, we let the collection of input-output pairs define the model itself.
Why black box models?
- A lot of work in ML interpretability requires access to things like internal activations or model weights, but most users don’t have this information. Even with access, memory and storage can limit scalability.
- The black box setting is more general and less computationally constrained, making it a great choice for anyone who wants to perform inference with model collections.
We can represent models as vectors by
The Discriminative Factorization framework is a way to decompose distances between black box models that allows us to analyze the impact of queries on the model representations.