FANoS-v2: Feedback-Controlled Momentum with Thermostat Damping for Lightweight Neural Optimization
\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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Flexibility management with virtual batteries of thermostatically controlled loads: real-time control system and potential in Spain
Virtual batteries composed of aggregated thermostatically controlled loads are able to provide real-time frequency regulation to electrical grids. Load flexibility management can be helpful in solving the problem of bala…
ManagementSetpoint Tracking with Partially Observed Loads
We use online convex optimization (OCO) for setpoint tracking with uncertain, flexible loads. We consider full feedback from the loads, bandit feedback, and two intermediate types of feedback: partial bandit where a subs…
Adaptive Momentum and Nonlinear Damping for Neural Network Training
Momentum Stochastic Gradient Descent (mSGD) relies on a fixed momentum coefficient shared across all parameters, failing to account for the heterogeneous structure of modern loss landscapes. In this work, we adopt a cont…
Aggregated Momentum: Stability Through Passive Damping
Momentum is a simple and widely used trick which allows gradient-based optimizers to pick up speed along low curvature directions. Its performance depends crucially on a damping coefficient $\beta$. Large $\beta$ values …
Model-Free Control of Thermostatically Controlled Loads Connected to a District Heating Network
Optimal control of thermostatically controlled loads connected to a district heating network is considered a sequential decision- making problem under uncertainty. The practicality of a direct model-based approach is com…
Decision MakingReinforcement LearningSequential Decision Making