Timezone: »

Information-constrained optimization: can adaptive processing of gradients help?
Jayadev Acharya · Clement Canonne · Prathamesh Mayekar · Himanshu Tyagi

Thu Dec 09 04:30 PM -- 06:00 PM (PST) @

We revisit first-order optimization under local information constraints such as local privacy, gradient quantization, and computational constraints limiting access to a few coordinates of the gradient. In this setting, the optimization algorithm is not allowed to directly access the complete output of the gradient oracle, but only gets limited information about it subject to the local information constraints. We study the role of adaptivity in processing the gradient output to obtain this limited information from it, and obtain tight or nearly tight bounds for both convex and strongly convex optimization when adaptive gradient processing is allowed.

Author Information

Jayadev Acharya (Cornell University)
Clement Canonne (University of Sydney)
Prathamesh Mayekar (Indian Institute of Science)
Himanshu Tyagi

More from the Same Authors