Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
Learning to Perturb Hidden Representations for Generalizable Deep Learning
Hua Li
Deep neural networks process data through a cascade of representations: input features, hidden activations, logits, and loss. While perturbations at the input, logit, and label lev…
cs.LG2026
Gradient Perturbation: Learning to Perturb Gradients for Adaptive Training
Hua Li
Deep neural network training involves both forward propagation (from features through logits to loss) and backward propagation (from loss through gradients to parameter updates). W…
cs.LG2022
The Counterfactual-Shapley Value: Attributing Change in System Metrics
Amit Sharma, Hua Li, Jian Jiao
Given an unexpected change in the output metric of a large-scale system, it is important to answer why the change occurred: which inputs caused the change in metric? A key componen…