Benchmarks

These notebooks reproduce experiments from Runje & Shankaranarayana (2023) using mononet. They are committed with their outputs and re-executed manually before each release — see CONTRIBUTING.md.

Each notebook also benchmarks against airtai/monotonic-nn (the paper’s original PyTorch reference) installed at notebook-execution time via --no-deps (see tools/execute-benchmarks.sh).

Sections

• Protocol — how we train, select, and report; and why our numbers differ from the original papers.

• Overview — high-level summary.

• Reproducing the paper — per-dataset notebooks and summary tables for all five benchmark datasets from the ICML 2023 paper.

• Flavor comparison — Phase 2a Optuna HP-search results comparing the four mode × residual flavors (absolute/switch × plain/residual).

• Deep-network init — the static absolute init that fixes moderate-depth trainability, and the deep-depth limitation it does not solve.