Implicit bias in overparameterized models emerges as a geometric correction induced by gradient noise and loss symmetries, enabling inverse design of desired biases like sparsity.
Stochastic gradient descent as approximate Bayesian inference.Journal of Machine Learning Research, 18(134):1–35
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Understanding and inverse design of implicit bias in stochastic learning: a geometric perspective
Implicit bias in overparameterized models emerges as a geometric correction induced by gradient noise and loss symmetries, enabling inverse design of desired biases like sparsity.