linear_datamodel_fit
Fit target-specific linear datamodel surrogates from subset membership vectors to observed target outcomes.
- License 许可
- Apache-2.0
- 最近更新
- 2026-09-03
- Stars
- ★ 351
- Forks
- 27
01 前言 Front Matter
- name
- linear_datamodel_fit
- description
- Fit target-specific linear datamodel surrogates from subset membership vectors to observed target outcomes.
02 资源文件 2
- 脚本scripts/fit_datamodel.py4.0 KB
- 脚本tests/test_fit_datamodel.py1.3 KB
03 SKILL.md 正文
Linear Datamodel Fit
Use this skill after subset-output pairs are available for a fixed target example. It preserves the paper mechanism of predicting f_A(x; S') from the binary characteristic vector of S'.
Inputs
- Binary membership matrix
Xwith one row per sampled subset. - Outcome vector
ywith one value per subset. - Optional ridge value for stable underdetermined fits.
Outputs
- Datamodel weights
theta. - Intercept.
- Predictions and diagnostics: Pearson correlation, MSE, and optional weight correlation.
Workflow
- Validate row counts and binary membership values.
- Add an intercept column.
- Solve least squares or ridge-regularized normal equations.
- Evaluate on held-out subsets, not only the fitted rows.
- Use learned weights as datamodel embeddings or pass them to counterfactual scoring.
Validation
Run:
python scripts/fit_datamodel.py --demo
python tests/test_fit_datamodel.py
Limitations
This skill fits the surrogate only; it does not create the base training subsets or train the original task model.
04 同仓库更多 Skills
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.
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.
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.
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.
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.
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).