A random shift of Gaussian inputs forces the first Hermite coefficient of any non-linear target to be large, yielding near-linear sample complexity independent of the target's information exponent, and a similar result holds for juntas.
SGD learning on neural networks: leap complexity and saddle-to-saddle dynamics
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Low-dimensional Functions are Efficiently Learnable under Randomly Biased Distributions
A random shift of Gaussian inputs forces the first Hermite coefficient of any non-linear target to be large, yielding near-linear sample complexity independent of the target's information exponent, and a similar result holds for juntas.