CNN regressor on contour plots of probed landscapes enables per-instance algorithm selection that outperforms the single best solver and competes with feature-based baselines on BBOB benchmarks.
A fast and elitist multiobjective genetic algorithm: Nsga-ii
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
A multi-objective Bayesian optimization framework co-optimizes CIM crossbar hardware and DNN parameters for VGG8/CIFAR-10 and VGG16/Tiny-ImageNet, achieving comparable accuracy with up to 65% smaller area and 52% lower energy.
citing papers explorer
-
Beyond Numerical Features: CNN-Driven Algorithm Selection via Contour Plots for Continuous Black-Box Optimization
CNN regressor on contour plots of probed landscapes enables per-instance algorithm selection that outperforms the single best solver and competes with feature-based baselines on BBOB benchmarks.
-
Bayesian Optimization of Crossbar-Based Compute-In-Memory System Design for Efficient DNN Inference
A multi-objective Bayesian optimization framework co-optimizes CIM crossbar hardware and DNN parameters for VGG8/CIFAR-10 and VGG16/Tiny-ImageNet, achieving comparable accuracy with up to 65% smaller area and 52% lower energy.