Presentation
TACo: Training-Free, Hardware-Aware ViT Architecture Search with a Hypervolume-Based Unified Zero-Cost Score
DescriptionWe propose TACo, a training-free, hardware-aware architecture search framework for Vision Transformers (ViTs), powered by a Hypervolume-based Unified Zero-Cost Score (HV-score) that integrates four accuracy- and hardware-related dimensions: a newly proposed zero-cost accuracy score (ZAS), latency, energy, and activation memory. TACo rapidly estimates the potential of candidate ViTs without training: ZAS captures layer-wise gradient stability, weight–gradient coupling, and gradient-modulated activation stability, while the HV-score guides multi-objective selection using Pareto and hypervolume principles. Experiments on CIFAR-10 and ImageNet-1K show that TACo reduces search time from GPU-days to GPU-hours while identifying a well-balanced ViT architecture in terms of accuracy and computational cost.
Event Type
Research Manuscript
TimeTuesday, July 285:18pm - 5:30pm PDT
LocationMtg Room 101A
Similar Presentations