pith:Z72TIE6M
Ergodic Trajectory Design by Learned Pushforward Maps: Provable Coverage via Conditional Flow Matching
A learned pushforward map turns an analytic uniform ergodic path into trajectories whose time-averaged occupancy matches any target density with error controlled by training loss.
arxiv:2605.13063 v1 · 2026-05-13 · cs.LG
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{Z72TIE6MHEOL2LUJCREIQ57OVN}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
The composed trajectory is asymptotically ergodic with respect to the learned pushforward distribution, with deviation from the target controlled by the flow-matching training loss; the three bounds combine into an end-to-end coverage bound estimable from CFM training diagnostics (certified given an architectural Lipschitz bound on v_θ).
That a single offline-trained conditional flow matching map can transport the exact uniform ergodic occupancy of the analytic latent trajectory onto an arbitrary target density while respecting all operational constraints, with the approximation error bounded solely by the training loss and a Lipschitz constant on the learned velocity field.
An analytic uniform ergodic latent trajectory is pushed forward by a conditional flow matching map to produce asymptotically ergodic trajectories matching any target density with provable coverage bounds.
References
Formal links
Receipt and verification
| First computed | 2026-05-18T03:08:59.039144Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
cff53413cc391cbd2e8914488877eeab711756544351396a482b03de40127188
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/Z72TIE6MHEOL2LUJCREIQ57OVN \
| jq -c '.canonical_record' \
| python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: cff53413cc391cbd2e8914488877eeab711756544351396a482b03de40127188
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "140fdf4a0d0fc34f1d63f78e2254f3b5ed82df3732fb519f77882420aafcb0c9",
"cross_cats_sorted": [],
"license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
"primary_cat": "cs.LG",
"submitted_at": "2026-05-13T06:34:08Z",
"title_canon_sha256": "3fe0a4f0daee464b4049d970f977a226b85e334e3ca85535bd5516d6a32514b4"
},
"schema_version": "1.0",
"source": {
"id": "2605.13063",
"kind": "arxiv",
"version": 1
}
}