Statistical Learning
Implicit Posterior Variational Inference for Deep Gaussian Processes
Haibin YU, Yizhou Chen, Bryan Kian Hsiang Low, Patrick Jaillet, Zhongxiang Dai
Neural Information Processing Systems http://nips.cc/
Trade-off Between Efficiency and Consistency for Removal-based Explanations
Nonetheless, these methods primarily emphasize efficiency in the original context, often resulting in general inconsistencies.
TowardsSample-efficientOverparameterized Meta-learning
An overarching goal in machine learning is to build ageneralizable model with fewsamples.
TowardsSample-efficientOverparameterized Meta-learning
We then integrate these findings toobtain anoverallperformance guarantee forourmetalearning algorithm.
An Empirical Investigation of Domain Generalization with Empirical Risk Minimizers (Appendix)
Proceedings of the International Conference on Machine Learning 2021
Learning Non-Convergent Non-Persistent Short-Run MCMC Toward Energy-Based Model
Erik Nijkamp, Mitch Hill, Song-Chun Zhu, Ying Nian Wu
Weprovideargumentsfortreating the learned non-convergent short-run MCMC as a valid model. We show thatthe learned short-run MCMC is capable of generating realistic images.
2bc8ae25856bc2a6a1333d1331a3b7a6-AuthorFeedback.pdf
After training, we learn the dynamicsx = Mθ(z),whereMθ consists18 of K-steps of gradient descent dynamics (the noise term of the Langevin dynamics is negligible compared to the19 gradient termafterlearning).