AGENT SKILL

posterior_two_sample_metrics

Compute deterministic posterior two-sample diagnostics including C2ST-style accuracy for SBI benchmark recovery.

License 许可
Apache-2.0
最近更新
2026-09-03
Stars
★ 351
Forks
27

01 前言 Front Matter

name
posterior_two_sample_metrics
description
Compute deterministic posterior two-sample diagnostics including C2ST-style accuracy for SBI benchmark recovery.

02 资源文件 2

03 SKILL.md 正文

Posterior Two-Sample Metrics

Use this skill when an SBI benchmark recovery needs a lightweight distributional comparison between reference posterior samples and approximate posterior samples. It is meant for bounded runs where sklearn is unavailable but C2ST-style evidence is still needed.

Do not use this skill to reproduce the exact paper MLP C2ST when the full sklearn and benchmark runtime is available. In that case, run the official metric or an equivalent library implementation and record it as the stronger evidence.

Inputs

  • JSON file with reference posterior samples.
  • JSON file with approximate posterior samples.
  • Optional acceptance threshold.

Outputs

  • Metric JSON with c2st_accuracy, c2st_distance_to_ideal, mmd2, counts, dimension, and interpretation.

Workflow

  1. Load both sample sets and validate shapes.
  2. Z-score using reference-sample statistics.
  3. Build a deterministic nearest-centroid classifier and evaluate it with balanced held-out folds.
  4. Report balanced accuracy and its absolute distance to the ideal value 0.5. Interpret this metric by closeness to 0.5, not as either a larger-is-better or lower-is-better score.
  5. Report squared distance between sample means as a small MMD-style diagnostic.

Validation

Run:

python scripts/posterior_two_sample_metrics.py self-test
python tests/test_posterior_two_sample_metrics.py

Limitations

The C2ST helper uses a deterministic nearest-centroid classifier, not the paper's MLP. It preserves the two-sample testing mechanism and interpretive scale for reduced recovery.

04 同仓库更多 Skills

VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-triton-opt

Make a single PassNet Triton kernel fast AND numerically faithful: performance model (when a replacement can win at all), block/grid/warp tuning, autotune policy, launch overhead, and per-op numeric recipes to pass the dtype baseline tolerances. Use when a pass matches and is correct but speedup below expected, or when correctness fails by small numeric margins.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-solve

END-TO-END playbook for solving one PassNet sample: analyze the computation graphs, decide the optimization strategy (what to fuse, what to replace, what to leave alone), drive the iteration loop, and maximize the sample score. This is the ENTRY skill — invoke it first for any PassNet optimization task; it tells you when to use passnet-pattern-fusion, passnet-triton-opt and passnet-feedback.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-skill

PassNet GPU kernel optimization via compiler passes. Design and implement Triton-based optimization passes, create pass files under ./pass_dir/, self-evaluate with pass_evaluator, and iterate to maximize GPU speedup.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-pattern-fusion

Author PassNet pass files: write patterns that actually MATCH the FX graph, pick fusion regions (which ops to absorb into one Triton kernel), and structure multi-pass submissions with the mandatory shared-dispatch architecture. Use when creating or fixing pattern()/replacement_args()/replacement_func() files, when a pass "failed to match", or when deciding how to fuse multiple kernels/ops.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-orchestrate

Round/batch planning and decision support for PassNet graph optimization. Use for multi-sample triage, worker allocation, eval-budget policy, and post-eval keep/revert decisions. For solving one concrete sample end to end, use passnet-solve as the entry skill; consult this skill only when you need broader planning or a specific decision gate.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-feedback

Fast, deterministic feedback for PassNet work: pre-flight pattern/match verification WITHOUT burning a GPU evaluation, per-node bottleneck analysis of a sample's graphs, and eval-log parsing into per-variant status + estimated score + failure classification. Use BEFORE every GPU evaluation (check_pattern), at the START of a sample (analyze_graph), and AFTER every evaluation (parse_eval_log).

★ 351