{"ID":2823708,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2601.00889","arxiv_id":"2601.00889","title":"FANoS-v2: Feedback-Controlled Momentum with Thermostat Damping for Lightweight Neural Optimization","abstract":"\\FANOS{} is a PyTorch optimizer that augments RMS-preconditioned momentum with a scalar feedback controller over update energy. The public reference implementation stores momentum in parameter-update units, applies a non-negative thermostat damping coefficient, supports diagonal, factored, and raw-gradient preconditioning, and exposes diagnostics intended for stability audits. This study gives a complete mathematical specification of the released optimizer, including the exact parameter-unit update, the study-equation physical update mode, bounded log-ratio thermostat control, adaptive preconditioner softening, warmup guardrails, and the experimental \\Fast{} profile. We report the v0.2 evidence: five-seed reduced-sample MNIST, Fashion-MNIST, and CIFAR-10 experiments show mean top-1 gains of 0.889, 2.197, and 2.666 percentage points over AdamW for \\Fast{}, but with 49.8\\%, 61.6\\%, and 56.8\\% higher wall-clock time. Preliminary scientific, PINN, and EEG smoke tests are mixed and are treated as hypothesis-generating only. The evidence supports \\FANOS{} as an alpha-stage research optimizer with a reproducible lightweight-vision signal and an explicit runtime bottleneck.","short_abstract":"\\FANOS{} is a PyTorch optimizer that augments RMS-preconditioned momentum with a scalar feedback controller over update energy. The public reference implementation stores momentum in parameter-update units, applies a non-negative thermostat damping coefficient, supports diagonal, factored, and raw-gradient precondition...","url_abs":"https://arxiv.org/abs/2601.00889","url_pdf":"https://arxiv.org/pdf/2601.00889v2","authors":"[\"Nalin Dhiman\"]","published":"2025-12-31T11:49:49Z","proceeding":"cs.LG","tasks":"[\"cs.LG\"]","methods":"[]","has_code":false}