A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Backpropagation-free RL method trains layers using local signals.
Backpropagation-free trunk training improves model performance on various benchmarks.
New learning rules for wide neural networks without backpropagation.
This paper presents a new family of backpropagation-free neural architectures, Gated Linear Networks (GLNs). What distinguishes GLNs from contemporary neural networks is the distributed and local nature of their credit assignment mechanism; each neuron directly predicts the target, forgoing the ability to learn feature…
FP uses random projections to train networks without feedback, achieving comparable performance to backpropagation.
Demon aligns diffusion models without retraining or backpropagation.
Paper identifies how neural networks learn features.