Reply to Reviewer 2, 3 and 4 Novelty of the analysis: Besides keeping the estimator of f(x k,y
–Neural Information Processing Systems
We are happy to cite this paper and compare it with SREDA. A more reasonable way is to solve it by accessing the (stochastic) gradient of f like SREDA. We are happy to follow the reviewer's suggestion and include it in the main text if the paper is accepted.
Neural Information Processing Systems
Mar-21-2025, 16:41:57 GMT
- Technology: