No AI summary available for this article.
Why It Matters
Saved checkpoints record states along a training trajectory, but generally do not determine the updates at states that would be visited under a different schedule.
Provenance
Discovered via ArXiv and published by ArXiv.
Key Claims
Original description
Saved checkpoints record states along a training trajectory, but generally do not determine the updates at states that would be visited under a different schedule. We study how accurately these checkpoints can reconstruct the endpoint of a sequential reference with prescribed update strengths. Under a common local transition model, two checkpoint-index moment conditions characterize all convex merges that agree with this reference through second order. We then prove an information limit that for nondegenerate profiles, no algorithm using only a fixed-length gradient-descent (GD) history with s...
Discovered via ArXiv
Research papers and preprints from arXiv.
Publisher: arxiv.org
ID: http://arxiv.org/abs/2609.35168v1 · Indexed about 1 hour ago