Repeating forward gradient descent updates on each sample ℓ times improves the linear-model error rate from d²/n to d²/(ℓ∧d)n, matching SGD when ℓ≈d.
Is Learning in Biological Neural Networks Based on StochasticGradientDescent?AnAnalysisUsingStochasticProcesses
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.ST 1years
2024 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
Improving the Convergence Rates of Forward Gradient Descent with Repeated Sampling
Repeating forward gradient descent updates on each sample ℓ times improves the linear-model error rate from d²/n to d²/(ℓ∧d)n, matching SGD when ℓ≈d.