Designing Compact Neural Architectures via Neuron Gating and Mixed Activation
Neural Architecture Search (NAS) is naturally formulated as a bilevel optimization problem, where the upper-level optimizes the architecture using validation performance and the lower-level trains network parameters using training loss. However, NAS is computationally expensive due to discrete architectural decisions, exponentially growing search spaces, and the high cost of training candidate architectures. This work develops a general bilevel optimization framework for NAS across diverse architectures, including MLPs, CNNs, RNNs, and Transformers, to identify compact architectures with stron
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 48%Transformer →
- PossiblePossibly related (embedding) · 46%Algorithm–hardware co-design of neuromorphic networks with dual memory pathways →
- LinkedLinked via arxiv author · 85%Abhishek Shukla →
“Designing Compact Neural Architectures via Neuron Gating and Mixed Activation”
- LinkedLinked via arxiv author · 85%Ankur Sinha →
“Designing Compact Neural Architectures via Neuron Gating and Mixed Activation”
- LinkedLinked via arxiv author · 85%Faiz Hamid →
“Designing Compact Neural Architectures via Neuron Gating and Mixed Activation”