Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
Same Loss, Different Gradients
Ningkang Peng, Xiaoqian Peng, Yifan He +4
Differentiable learning typically assumes that the scalar objective evaluated in the forward pass and the gradient supplied to the optimizer in the backward pass describe the same…
cs.LG2026
Does a Shared Temperature Imply a Shared Angular Scale in Probabilistic Contrastive Learning?
Ningkang Peng, Qianfeng Yu, Jingyang Mao +4
In probabilistic contrastive learning, a shared temperature is commonly interpreted as a shared similarity scale, but this interpretation does not hold for high-dimensional distrib…
cs.LG2026
When Accuracy Is Not Enough: Uncertainty Collapse between Noisy Label Learning and Out-of-Distribution Detection
Ningkang Peng, Jingyang Mao, Runhan Zhou +2
Learning with noisy labels (LNL) is typically benchmarked by closed-set classification accuracy, yet deployment often requires classifiers to reject out-of-distribution (OOD) input…