- Rating
- 3(+1)
- Confidence
- 2
- Informativeness
- 1
- Presentation
- 1
- Soundness
- 1
Read review
Paper summary
The paper studies predictors that process an initial sample nonlinearly, then fix an affine map for the remaining observations. For signals lying on a known smooth manifold, it characterizes how prediction risk depends on the initial sample size. For signals on a smooth manifold, it characterizes how prediction risk depends on the initial sample size and the manifold’s geometry.
Critical strengths
-
The matching upper and lower bounds characterize the statistical cost of nonlinear processing,
-
The observation that successive derivative directions determine the leading risk is interesting.
Critical weaknesses
-
The meaning of “nonlinear label budget” is difficult to understand from the introduction and the restriction concerns how observations are processed. The paper introduces complivated terminologies in rapid succession, without any examples. Thus, it is difficult to identify which restriction creates the statistical difficulty.
-
The main results concern Gaussian observations of a known manifold signal, while the image experiments use sparse pixels and source-fitted conditional moments.
-
The geometric minimax results appear interesting, but the presentation makes their meaning and relationship to the applications unnecessarily difficult to assess
Questions for authors
-
Can the authors give one concrete observation-to-prediction example, explicitly stating which operations are permitted before and after the pilot, and use it to explain the main theorems?
-
Which conclusions from the Gaussian manifold theory apply to the sparse-pixel experiments?