From 18aff5b55e3ad1f6e244ad25a8eae44f25f4e5c1 Mon Sep 17 00:00:00 2001 From: YurenHao0426 Date: Wed, 22 Jul 2026 13:48:59 -0500 Subject: protocol: freeze residual mirror baseline funnel --- README.md | 1 + RESIDUAL_MIRROR.md | 73 ++++++++++++ experiments/analyze_residual_mirror_capture.py | 153 +++++++++++++++++++++++++ experiments/residual_mirror_capture_screen.py | 54 +++++++++ 4 files changed, 281 insertions(+) create mode 100644 RESIDUAL_MIRROR.md create mode 100644 experiments/analyze_residual_mirror_capture.py create mode 100644 experiments/residual_mirror_capture_screen.py diff --git a/README.md b/README.md index b49774c..0a4d9e4 100644 --- a/README.md +++ b/README.md @@ -147,6 +147,7 @@ the observed child response and learns only from the local prediction error; unlike WM, its update is zero for every probe at exact symmetry. The extra feedback prediction convolution is charged explicitly, and this rule receives no SDIL novelty credit. +`RESIDUAL_MIRROR.md` freezes its capture and conditional task gates. The subsequent V3 mechanism estimates the required A/G matrix statistics directly by perturbing the vectorizer parameter subspace. It remains diff --git a/RESIDUAL_MIRROR.md b/RESIDUAL_MIRROR.md new file mode 100644 index 0000000..312bc35 --- /dev/null +++ b/RESIDUAL_MIRROR.md @@ -0,0 +1,73 @@ +# Residual response-mirror baseline protocol + +## Status and method boundary + +Estimate-then-average WM passed its frozen capture gate but missed the short +accuracy gate by under one point. Its final feedback/forward cosine plateaued +near 0.81 in the deepest convolutional group despite frequent local probes. +The diagnosed issue is stationary estimator noise: a fresh finite-sample W +estimate is noisy even when Q already equals W. + +Residual response mirroring (RRM) is a substantive update-rule change, not a +new cadence/batch/rate branch of failed WM. For each local Gaussian probe it +compares the observed forward child response with Q's predicted response and +updates from their difference. At Q=W, every individual stochastic update is +zero. The observation and update remain separated; the update never reads a +forward parameter. RRM is still inherited local predictive weight estimation, +not SDIL or Harnett-specific novelty. + +A mechanics-only synthetic-image pilot was used to bound the mirror-rate grid. +No CIFAR development-prefix alignment or validation/test endpoint was observed +before this protocol and its executable selector were committed. + +## RRM-0: mechanics gate + +The convolutional smoke suite must verify: + +- exact-symmetry response-residual fraction below `1e-14` for every probe; +- exact-symmetry parameter-update RMS below `1e-14`; +- changing all forward parameters after observations are fixed changes the + feedback update by exactly zero; +- all prior hierarchical and local-gradient checks remain green. + +This passes at response-residual fraction `3.08e-17`, update RMS `2.75e-18`, +and forward-parameter independence error exactly zero. + +## RRM-1: frozen-forward capture gate + +Copy WM-1 exactly: seed-0 ResNet-20, random feedback scale 1, frozen 10k +development prefix, 64-example exact-gradient audit, convolutional mirror batch +1, Gaussian noise standard deviation 1, mirror seed 3000, 20 observations, and +no forward/readout/BatchNorm update. Record fixed HFA and cross +`eta_M in {0.03,0.1,0.3}`. Select early alignment, then all-layer alignment, +then lower rate. + +All four records must be finite, and selected RRM must reach early alignment +0.65, all-layer alignment 0.70, mean feedback/forward cosine 0.93, norm ratios +in `[0.5,1.5]`, and zero task-loss queries. No extra observation, rate, batch, +noise, cadence, or layer-specific setting follows a failure. + +## RRM-2: short accuracy gate + +Only an RRM-1 pass opens two 10k-example, 20-epoch ResNet-20 validation jobs. +Copy WM-2 exactly: hidden LR `{0.03,0.1}`, output LR 0.1, batch 128, cosine +decay, no warmup, momentum 0.9, weight decay `1e-4`, 20 mirror warmup +observations, then one batch-1 observation every 16 task updates. The extra Q +response-prediction convolution is charged explicitly. + +Select accuracy, then total MACs/rate. Both records must be finite; selected +RRM must reach 65%, lie within 10 points of matched BP 74.94%, retain early +alignment 0.50, use zero task-loss queries for feedback learning, and cost no +more than 1.15x matched BP MACs. Failure closes RRM. + +## RRM-3: conditional full baseline + +Only an RRM-2 pass opens one 200-epoch seed-0 validation run, copying selected +settings and the A1 epoch-100/150 step drops on all 45,000 development-training +examples. It must be finite, reach 88%, retain early alignment 0.50, and cost +at most 1.15x BP. It does not authorize test access. A pass instead freezes the +same scalable substrate for a raw-versus-innovation mixed-traffic experiment. + +RRM is a baseline throughout. RRM-1/RRM-2 cannot raise the reviewer score; +only a later load-bearing innovation result on top of it can do so. + diff --git a/experiments/analyze_residual_mirror_capture.py b/experiments/analyze_residual_mirror_capture.py new file mode 100644 index 0000000..361aba8 --- /dev/null +++ b/experiments/analyze_residual_mirror_capture.py @@ -0,0 +1,153 @@ +#!/usr/bin/env python3 +"""Audit and gate residual-response mirror causal capture.""" +import argparse +import glob +import json +import math +import os + + +SPLIT_HASH = "8328b206a97c420e49e54e3eca4abe3274c4756b084355784ea3fb8059e4515b" +RATES = (0.03, 0.1, 0.3) + + +def load(path): + with open(path) as handle: + record = json.load(handle) + args = record["args"] + mode = args.get("mode") + if mode not in ("hfa", "rrm"): + raise ValueError(f"{path}: unexpected method") + expected = { + "depth": 20, "width": 16, "seed": 0, "loader_seed": 0, + "epochs": 0, "train_limit": 10000, "val_examples": 5000, + "split_seed": 2027, "eval_split": "validation", "eval_every": 0, + "normalization": "batchnorm", "a_scale": 1.0, + "alignment_probe": 64, "mirror_batch_size": 1, + "mirror_noise_std": 1.0, "mirror_seed": 3000, + } + for key, value in expected.items(): + if args.get(key) != value: + raise ValueError(f"{path}: {key} drift") + expected_steps = 0 if mode == "hfa" else 20 + if args.get("mirror_warmup_steps") != expected_steps: + raise ValueError(f"{path}: mirror warmup drift") + if mode == "rrm" and float(args["mirror_eta"]) not in RATES: + raise ValueError(f"{path}: unregistered mirror rate") + if record["provenance"]["git_tracked_dirty"]: + raise ValueError(f"tracked-dirty result: {path}") + if record["split"]["validation_index_sha256"] != SPLIT_HASH: + raise ValueError(f"split drift: {path}") + if record["evaluation_protocol"]["test_evaluations"]: + raise ValueError(f"test touched: {path}") + expected_space = (None if mode == "hfa" + else "local_parent_child_response_residual") + if record.get("calibration_metric_space") != expected_space: + raise ValueError(f"metric-space drift: {path}") + diagnostics = record["diagnostics"] + values = diagnostics["teaching_negative_gradient_cosine"] + early_count = max(1, len(values) // 3) + norm_ratios = diagnostics["feedback_forward_norm_ratio"] + feedback_cosines = diagnostics["feedback_forward_cosine"] + metrics = { + "early_third_alignment": sum(values[:early_count]) / early_count, + "all_layer_alignment": sum(values) / len(values), + "mean_feedback_forward_cosine": ( + sum(feedback_cosines) / len(feedback_cosines)), + "min_feedback_forward_norm_ratio": min(norm_ratios), + "max_feedback_forward_norm_ratio": max(norm_ratios), + } + if mode == "rrm": + warmup = record.get("mirror_warmup", {}).get("mean") + if warmup is None: + raise ValueError(f"missing RRM aggregate: {path}") + metrics.update({ + "mean_mirror_update_rms": warmup["mirror_update_rms"], + "mean_response_residual_rms": ( + warmup["mirror_response_residual_rms"]), + "mean_response_residual_fraction": ( + warmup["mirror_response_residual_fraction"]), + }) + finite = (bool(record["final"]["finite"]) + and all(math.isfinite(value) for value in metrics.values())) + return { + "path": path, "mode": mode, + "mirror_eta": (None if mode == "hfa" else float(args["mirror_eta"])), + "metrics": metrics, "finite": finite, + "logical_batch_loss_queries": int( + record["work"]["logical_batch_loss_queries"]), + "mirror_events": int(record["counters"]["mirror_events"]), + "total_macs": int(record["work"]["total_macs_estimate"]), + "source_commit": record["provenance"]["git_commit"], + } + + +def main(): + parser = argparse.ArgumentParser() + parser.add_argument("--input", default="results/residual_mirror_capture") + parser.add_argument( + "--out", default="results/residual_mirror_capture_gate.json") + args = parser.parse_args() + rows = [load(path) for path in sorted( + glob.glob(os.path.join(args.input, "*.json")))] + references = [row for row in rows if row["mode"] == "hfa"] + candidates = [row for row in rows if row["mode"] == "rrm"] + if len(references) != 1 or len(candidates) != len(RATES): + raise ValueError("incomplete RRM-1 method grid") + if {row["mirror_eta"] for row in candidates} != set(RATES): + raise ValueError("incomplete RRM-1 rate grid") + if len({row["source_commit"] for row in rows}) != 1: + raise ValueError("RRM-1 source commits differ") + eligible = [row for row in candidates if row["finite"]] + eligible.sort(key=lambda row: ( + -row["metrics"]["early_third_alignment"], + -row["metrics"]["all_layer_alignment"], row["mirror_eta"])) + selected = eligible[0] if eligible else None + checks = { + "all_four_records_finite": all(row["finite"] for row in rows), + "candidate_selected": selected is not None, + } + if selected is None: + checks.update({ + "early_third_at_least_0.65": False, + "all_layer_at_least_0.70": False, + "mean_feedback_forward_cosine_at_least_0.93": False, + "feedback_norm_ratios_in_0.5_to_1.5": False, + "zero_task_loss_queries": False, + }) + else: + metrics = selected["metrics"] + checks.update({ + "early_third_at_least_0.65": ( + metrics["early_third_alignment"] >= 0.65), + "all_layer_at_least_0.70": ( + metrics["all_layer_alignment"] >= 0.70), + "mean_feedback_forward_cosine_at_least_0.93": ( + metrics["mean_feedback_forward_cosine"] >= 0.93), + "feedback_norm_ratios_in_0.5_to_1.5": ( + metrics["min_feedback_forward_norm_ratio"] >= 0.5 + and metrics["max_feedback_forward_norm_ratio"] <= 1.5), + "zero_task_loss_queries": all( + row["logical_batch_loss_queries"] == 0 for row in rows), + }) + output = { + "protocol": "residual_response_mirror_capture_v1", + "status": "passed" if all(checks.values()) else "failed", + "checks": checks, "rows": rows, "matched_fixed_hfa": references[0], + "selected_rrm": selected, "confirmation_test_seeds_touched": False, + "review_score_before": 5, "review_score_after": 5, + "score_change_rule": "inherited baseline capture cannot raise score", + } + os.makedirs(os.path.dirname(os.path.abspath(args.out)), exist_ok=True) + with open(args.out, "w") as handle: + json.dump(output, handle, indent=2, sort_keys=True) + handle.write("\n") + print(json.dumps({ + "status": output["status"], "checks": checks, + "reference": references[0], "selected_rrm": selected, + }, indent=2)) + + +if __name__ == "__main__": + main() + diff --git a/experiments/residual_mirror_capture_screen.py b/experiments/residual_mirror_capture_screen.py new file mode 100644 index 0000000..223a1db --- /dev/null +++ b/experiments/residual_mirror_capture_screen.py @@ -0,0 +1,54 @@ +#!/usr/bin/env python3 +"""Run a shard of the frozen residual-response mirror capture screen.""" +import argparse +import os +import subprocess +import sys + + +def main(): + parser = argparse.ArgumentParser() + parser.add_argument("--device", default="cuda") + parser.add_argument("--shard_index", type=int, default=0) + parser.add_argument("--num_shards", type=int, default=1) + parser.add_argument("--dry_run", action="store_true") + args = parser.parse_args() + if not 0 <= args.shard_index < args.num_shards: + raise ValueError("invalid shard index") + common = [ + sys.executable, "experiments/conv_run.py", "--device", args.device, + "--depth", "20", "--width", "16", "--seed", "0", + "--loader_seed", "0", "--batch_size", "128", "--epochs", "0", + "--train_limit", "10000", "--val_examples", "5000", + "--split_seed", "2027", "--eval_split", "validation", + "--eval_every", "0", "--augment_train", "1", "--lr", "0.1", + "--output_lr", "0.1", "--lr_schedule", "constant", + "--warmup_epochs", "0", "--momentum", "0.9", + "--weight_decay", "1e-4", "--normalization", "batchnorm", + "--a_scale", "1", "--alignment_probe", "64", + "--mirror_batch_size", "1", "--mirror_noise_std", "1", + "--mirror_seed", "3000", + ] + jobs = [("fixed_hfa", common + [ + "--mode", "hfa", "--out", + "results/residual_mirror_capture/fixed_hfa.json", + ])] + for rate in (0.03, 0.1, 0.3): + tag = f"rrm_etaM{rate}" + jobs.append((tag, common + [ + "--mode", "rrm", "--mirror_eta", str(rate), + "--mirror_warmup_steps", "20", "--out", + f"results/residual_mirror_capture/{tag}.json", + ])) + os.makedirs("results/residual_mirror_capture", exist_ok=True) + for index, (tag, command) in enumerate(jobs): + if index % args.num_shards != args.shard_index: + continue + print(tag, " ".join(command), flush=True) + if not args.dry_run: + subprocess.run(command, check=True) + + +if __name__ == "__main__": + main() + -- cgit v1.2.3