AGENT SKILL

ewc_recovery_evaluation

Run a bounded EWC retention recovery comparison and emit validator-compatible result, trace, and mechanism-check artifacts.

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

01 前言 Front Matter

name
ewc_recovery_evaluation
description
Run a bounded EWC retention recovery comparison and emit validator-compatible result, trace, and mechanism-check artifacts.

02 资源文件 2

03 SKILL.md 正文

EWC Recovery Evaluation

Use this skill to execute a reduced or full sequential-training comparison for Elastic Weight Consolidation. It should be used after task protocol, Fisher importance, and EWC penalty skills are available.

Inputs

  • Protocol JSON with task order and datasets.
  • Generated skill root containing ewc_task_protocol, ewc_fisher_importance, and ewc_penalty.
  • Module-plan target metadata.
  • Output paths for recovery artifacts.

Outputs

  • recovery_result.json with numeric retention metrics and mechanism checks.
  • training_trace.json with before/after loss and parameter values.
  • Skill invocation evidence proving generated modules were used.

Workflow

  1. Fit task A and snapshot parameters.
  2. Estimate a diagonal Fisher from task-A gradients.
  3. Train task B with plain SGD and with EWC.
  4. Compare task-A retention and Fisher-weighted drift.
  5. Save command-produced recovery artifacts.

Validation

Run:

python tests/test_recovery_evaluation.py

Limitations

The bundled harness is a reduced synthetic proxy. It does not claim full permuted-MNIST or Atari reproduction.

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