no code implementations • 6 Dec 2021 • Chunlin Ji, Hanchu Shen, Zhan Xiong, Feng Chen, Meiying Zhang, Huiwen Yang
Then We propose three information-theoretic loss functions for deterministic GZSL model: a mutual information loss to bridge seen data and target classes; an uncertainty-aware entropy constraint loss to prevent overfitting when using seen data to learn the embedding of target classes; a semantic preserving cross entropy loss to preserve the semantic relation when mapping the semantic representations to the common space.
no code implementations • 2 Dec 2019 • Chunlin Ji, Haige Shen
Recently various divergences have been proposed to design the surrogate loss for variational inference.
no code implementations • pproximateinference AABI Symposium 2019 • Chunlin Ji, Bin Liu, Yingkai Jiang, Ke Deng
We propose an evidence upper bound (EUBO) to act as the surrogate loss, and fit a DP mixture to the given data by minimizing the EUBO, which is equivalent to minimizing the KL-divergence between the target distribution and the DP mixture.
no code implementations • pproximateinference AABI Symposium 2019 • Chunlin Ji, Jiangsheng Yi, Wanchuang Zhu
Approximate Bayesian Computation (ABC) provides a generic framework of Bayesian inference for likelihood-free models, but sampling based posterior approximation is often time-consuming and has difficulty accessing the convergence.