{"ID":2852354,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.18808","arxiv_id":"2510.18808","title":"Does Feedback Alignment Work at Biological Timescales?","abstract":"Feedback alignment and related weight-transport-free algorithms are often proposed as biologically plausible alternatives to backpropagation, yet they are typically formulated in discrete phases with implicitly synchronized forward and error signals. We develop a continuous-time model of feedback-alignment-type learning in which neural activities and synaptic weights evolve together under coupled first-order dynamics with distinct propagation, plasticity, and decay time constants. We show that learning is governed by the temporal overlap between presynaptic drive and a locally projected error signal, providing an analytic explanation for robustness to moderate timing mismatch and for failure when mismatch eliminates overlap. Our results show that in order for feedback-alignment-type algorithms to work at biological timescales, they must obey the same temporal overlap principle that applies to other biological processes like eligibility traces.","short_abstract":"Feedback alignment and related weight-transport-free algorithms are often proposed as biologically plausible alternatives to backpropagation, yet they are typically formulated in discrete phases with implicitly synchronized forward and error signals. We develop a continuous-time model of feedback-alignment-type learnin...","url_abs":"https://arxiv.org/abs/2510.18808","url_pdf":"https://arxiv.org/pdf/2510.18808v2","authors":"[\"Marc Gong Bacvanski\",\"Liu Ziyin\",\"Tomaso Poggio\"]","published":"2025-10-21T17:04:06Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"q-bio.NC\"]","methods":"[]","has_code":false}