sensitivity analysis
The evaluation of how sensitive the output of a model is to changes in input or parameters, helping in understanding model robustness and reliability.
- DP-LLM: Runtime Model Adaptation with Dynamic Layer-wise Precision Assignment
- Differentially Private Relational Learning with Entity-level Privacy Guarantees
- Lie Detector: Unified Backdoor Detection via Cross-Examination Framework
- MM-OPERA: Benchmarking Open-ended Association Reasoning for Large Vision-Language Models
- Multi-Class Support Vector Machine with Differential Privacy
- Omnipresent Yet Overlooked: Heat Kernels in Combinatorial Bayesian Optimization
- Per-Architecture Training-Free Metric Optimization for Neural Architecture Search
- Private Geometric Median in Nearly-Linear Time
- Private Statistical Estimation via Truncation
- Resource-Constrained Federated Continual Learning: What Does Matter?
- SECA: Semantically Equivalent and Coherent Attacks for Eliciting LLM Hallucinations