For a two-layer binary network with Gaussian inputs, O(n^2) samples guarantee ergodic convergence of STE training and O(n^4) guarantee that iterates revisit the optimal weights, even under label noise.
Mirror descent view for neural network quantization
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
Beyond Discreteness: Sample Complexity Analysis of Straight-Through Estimator for 1-bit Quantization
For a two-layer binary network with Gaussian inputs, O(n^2) samples guarantee ergodic convergence of STE training and O(n^4) guarantee that iterates revisit the optimal weights, even under label noise.