AI & ML
Wait to Learn: Lobes and Dead Zones in Physical Backpropagation over an Aging Single-Antenna Channel
arXiv math.IT0 views
arXiv:2610.23135v1 Announce Type: cross Abstract: Sometimes the best way to correct an aged gradient is to wait. In physical backpropagation, a receiver returns its loss gradient through the reciprocal channel. With a single moving antenna, the mean gradient returned at the antenna is the true one counter-rotated by the phase of the temporal correlation. In simulation, uncorrected training fails in negative correlation lobes and revives in positive ones. At correlation zeros the return is independent of the forward channel, so no linear correction has a mean to recover; near them, more calibration barely helps, but holding the return until the next correlation extremum does.
Source:https://arxiv.org/abs/2610.23135PreviousKeep Pace to Learn: Movable Antennas Restore the Backpropagated Gradient Under User MobilityNextCoherent but Discordant: Rotate, Don't Invert, to Backpropagate Through an Aging Channel
Related posts
Scrape LinkedIn job postings without logging in (Python + Google Sheets)
0dev.to
Same model, same defences: 7 document attacks down to 0, chat attacks barely moved
0dev.to
Skill to Create Product Videos
0Hacker News
SOML – A Config Format for Humans
0Hacker News
Egoless Mathematics in the AI Era
0Hacker News
LifeVal
0OpenAI Blog