Temporal correlations from lazy random walks enable efficient SGD learning of k-juntas via temporal-difference loss on ReLU networks, achieving linear sample complexity in d.
Neural architecture search on imagenet in four gpu hours: A theoretically inspired perspective
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
Reviews NAS methods through bilevel optimization lens, categorizing them into sampling-based and theory-based, and proposes an auxiliary math programming framework for more principled architecture and weight updates.
A survey of Spiking Neural Network architecture search techniques viewed through a hardware/software co-design lens.
citing papers explorer
-
The Benefits of Temporal Correlations: SGD Learns k-Juntas from Random Walks Efficiently
Temporal correlations from lazy random walks enable efficient SGD learning of k-juntas via temporal-difference loss on ReLU networks, achieving linear sample complexity in d.
-
Bilevel Optimization for Neural Architecture Search
Reviews NAS methods through bilevel optimization lens, categorizing them into sampling-based and theory-based, and proposes an auxiliary math programming framework for more principled architecture and weight updates.
-
Spiking Neural Network Architecture Search: A Survey
A survey of Spiking Neural Network architecture search techniques viewed through a hardware/software co-design lens.