Derivative Convolutional Perceptron Separation
Descriptions may be stale. Consult the linked Lean sources.
Derivative Convolutional Perceptron Separation
We seek to separate samples
Equip the feature space
Our assumptions:
Assumption 1 (Background and derivative separation).
There exist scalars
Assumption 2 (Contrast scale). The contrast and
background scales satisfy
At any query
Results
Signed samples
| Result | Oracle complexity | Novelty | Limitations |
|---|---|---|---|
| (1) DerivativeConvolutionalPerceptronAcceleration (Ours) (review) | |||
| (2) Reconstruction, derived bound (Ordinary-Start Convolutional Perceptron Acceleration on Many Samples, n.d.) | (1): avoids storing samples and offline separation; no established oracle-complexity improvement. | (1): larger bound by
|
|
| (3) Fixed difference-filter perceptron, derived bound (Ordinary-Start Convolutional Perceptron Acceleration on Many Samples, n.d.) | (1): new ordinary-start learned-filter trajectory analysis; no established problem-class improvement over (3). | (1): larger bound by
|
|
| (4) Frozen raw-filter perceptron (Ordinary-Start Convolutional Perceptron Acceleration on Many Samples, n.d.) | Lower bound |
(1): method-specific gain
when |
|
| (5) (Tyurin 2026), Theorem 5.1 | (1): deterministic ordinary start and arbitrary sample count on a different derivative-separable class. Rates are incomparable; (5) includes a pure-constant sample excluded by (1). | (1) does not cover (5)’s dataset; requires nonzero backgrounds and the stated strong contrast condition. |
Abbr: