Under a piecewise-polynomial utility structure and a regularity condition, tuning one hyperparameter across tasks needs O(sqrt((log N + d log(Delta M) + log(1/delta))/m)) tasks for near-optimal average utility.
Sparse linear networks with a fixed butterfly structure: theory and practice
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
-
Sample complexity of data-driven tuning of model hyperparameters in neural networks with structured parameter-dependent dual function
Under a piecewise-polynomial utility structure and a regularity condition, tuning one hyperparameter across tasks needs O(sqrt((log N + d log(Delta M) + log(1/delta))/m)) tasks for near-optimal average utility.