- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper studies identifiability in nonlinear ICA without auxiliary variables for cases where the generating functions are real analytic and the source probability density functions have finitely many discontinuities in their first derivatives. The Laplace distribution is the main example. Experiments on real and synthetic data with Normalising Flows and Variational Autoencoders show the identifiability properties.
Critical strengths
- No regulariser or auxiliary information is needed for real analytic networks, so the results plausibly apply to existing pipelines.
- The synthetic study varies activation functions and source distributions and shows a consistent pattern with the theory.
Critical weaknesses
- There are some potential gaps between the theorem and the trained models. For example, the learned by a dense flow with element-wise tanh or sigmoid activations, and softplus, is mapped onto , and thus is not a diffeomorphism onto the support of a Laplace distribution and is not covered by Theorem 1. Meanwhile, no existing nICA baselines, e.g., methods discussed in related work, are compared on synthetic data.
- Several steps in the theorem may need more careful statements. For example, Step 2 concludes that "on an open neighbourhood of ". However, an open set in would contradict invertibility.
Questions for authors
- Please check the experimental settings and discuss the potential gaps with the theoretical settings.
- It is suggested to include an empirical comparison with related nICA baselines in the controlled setting where MCC is measurable.
- Please carefully check theoretical statements for improved readability and rigour.
We have uploaded a revision. See the paragraph starting on line 188 for an explanation of the translation ambiguity class.