Approximate leave-one-out (ALO) refers to methods that provide computationally efficient and statistically accurate approximations to leave-one-out risk estimation. These methods have recently attracted increased attention because of their connections to other important problems, including machine unlearning and data v...
Hong-Hao Lin, Song-Bin Liu, Arian Maleki et al.· 0 citations
This paper develops a unified framework for instance optimal sparse recovery from nonlinear observations. The main ingredient is a signal-dependent restricted approximate invertibility condition (RAIC) of some gradient, which leads to the instance optimality of iterative hard thresholding. Under Gaussian designs, we ap...
Two algorithms, MAGE and SPELL, suited for reconstruction and attribution respectively, are presented, that run on existing metagradient machinery at no extra cost and demonstrate strong performance over existing baselines across training scales and measurement budgets.
Yu-Xi Chen, Hamza Golubovic, Han Tong et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.