Behavior of Hyper-Parameters for Selected Machine Learning Algorithms: An Empirical Investigation

no code implementations • 15 Nov 2022 • Anwesha Bhattacharyya, Joel Vaughan, Vijayan N. Nair

Hyper-parameters (HPs) are an important part of machine learning (ML) model development and can greatly influence performance.

Improving the Reconstruction of Disentangled Representation Learners via Multi-Stage Modeling

no code implementations • 25 Oct 2020 • Akash Srivastava, Yamini Bansal, Yukun Ding, Cole Lincoln Hurwitz, Kai Xu, Bernhard Egger, Prasanna Sattigeri, Joshua B. Tenenbaum, Phuong Le, Arun Prakash R, Nengfeng Zhou, Joel Vaughan, Yaquan Wang, Anwesha Bhattacharyya, Kristjan Greenewald, David D. Cox, Dan Gutfreund

Current autoencoder-based disentangled representation learning methods achieve disentanglement by penalizing the (aggregate) posterior to encourage statistical independence of the latent factors.

Disentanglement