This doc contains an evolving list of papers related to Parameter Prediction for Unseen Deep Architectures (NeurIPS 2021) by Boris Knyazev, Michal Drozdzal, Graham Taylor and Adriana Romero-Soriano.
The main purpose of this list is to extend the related work section from our paper with more works, but some overlap between this list and our related work is okay.
The list is not structured by topics for now, which may be improved in the future.
Abhishek Sinha, Aahitagni Mukherjee, Mausoom Sarkar, Balaji Krishnamurthy. Introspection: Accelerating Neural Network Training By Learning Weight Evolution. ICLR 2017.
Vivek Ramanujan, Mitchell Wortsman, Aniruddha Kembhavi, Ali Farhadi, Mohammad Rastegari. What's Hidden in a Randomly Weighted Neural Network? CVPR 2020.
Jungtaek Kim, Saehoon Kim, Seungjin Choi. Learning to Warm-Start Bayesian Hyperparameter Optimization. NeurIPS 2017 workshop.