الباحثون

Peirong Ma

المنشورات 2

نسخة أولية وصول مفتوح

Does a Shared Temperature Imply a Shared Angular Scale in Probabilistic Contrastive Learning?

Ningkang Peng, Qianfeng Yu, Jingyang Mao وآخرون · 2026

In probabilistic contrastive learning, a shared temperature is commonly interpreted as a shared similarity scale, but this interpretation does not hold for high-dimensional distributional class representations. We study the exact von Mises-Fisher (vMF) probabilistic score used by ProCo when representation dimension and …

نسخة أولية وصول مفتوح

Same Loss, Different Gradients

Ningkang Peng, Xiaoqian Peng, Yifan He وآخرون · 2026

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 mathematical object. We show that this correspondence can fail when probabilistic objectives rely on finite special-function recurrences, cu …

المؤلفون المشاركون

Ningkang Peng Xiaoqian Peng Yifan He Anjie Hu Chao Tan Yanhui Gu Qianfeng Yu Jingyang Mao Tingyu Lu