A sampling-based statistical method bounds ViT soft-error failure rates with 99% confidence using thousands of injections and up to 10,700x cost reduction versus exhaustive testing.
Mix-and-match pruning: Globally guided layer-wise sparsification of dnns,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
HASA computes client heterogeneity scores from local data and assigns wider subnets to less heterogeneous clients, raising mean client test accuracy from 13.82% to 14.32% and improving worst-client accuracy versus uniform and partial-training baselines under matched compute budgets on a seven-client
citing papers explorer
-
SENTRY: Statistical Reliability Analysis of Vision Transformers Under Soft Errors
A sampling-based statistical method bounds ViT soft-error failure rates with 99% confidence using thousands of injections and up to 10,700x cost reduction versus exhaustive testing.
-
HASA: Subnet Allocation for Compute-Constrained Model-Heterogeneous Federated Learning
HASA computes client heterogeneity scores from local data and assigns wider subnets to less heterogeneous clients, raising mean client test accuracy from 13.82% to 14.32% and improving worst-client accuracy versus uniform and partial-training baselines under matched compute budgets on a seven-client