Efficient Low-Rank Semidefinite Programming with Robust Loss Functions
نویسندگان
چکیده
منابع مشابه
Computational enhancements in low-rank semidefinite programming
We discuss computational enhancements for the low-rank semidefinite programming algorithm, including the extension to block semidefinite programs, an exact linesearch procedure, and a dynamic rank reduction scheme. A truncated Newton method is also introduced, and several preconditioning strategies are proposed. Numerical experiments illustrating these enhancements are provided.
متن کاملFast Low-Rank Semidefinite Programming for Embedding and Clustering
Many non-convex problems in machine learning such as embedding and clustering have been solved using convex semidefinite relaxations. These semidefinite programs (SDPs) are expensive to solve and are hence limited to run on very small data sets. In this paper we show how we can improve the quality and speed of solving a number of these problems by casting them as low-rank SDPs and then directly...
متن کاملThe Mixing method: coordinate descent for low-rank semidefinite programming
In this paper, we propose a coordinate descent approach to low-rank structured semidefinite programming. The approach, which we call the Mixing method, is extremely simple to implement, has no free parameters, and typically attains an order of magnitude or better improvement in optimization performance over the current state of the art. We show that for certain problems, the method is strictly ...
متن کاملLocal Minima and Convergence in Low-Rank Semidefinite Programming
The low-rank semidefinite programming problem LRSDPr is a restriction of the semidefinite programming problem SDP in which a bound r is imposed on the rank of X, and it is well known that LRSDPr is equivalent to SDP if r is not too small. In this paper, we classify the local minima of LRSDPr and prove the optimal convergence of a slight variant of the successful, yet experimental, algorithm of ...
متن کاملRobust Semidefinite Programming∗
In this paper, we consider semidefinite programs where the data is only known to belong to some uncertainty set U . Following recent work by the authors, we develop the notion of robust solution to such problems, which are required to satisfy the (uncertain) constraints whatever the value of the data in U . Even when the decision variable is fixed, checking robust feasibility is in general NP-h...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: IEEE Transactions on Pattern Analysis and Machine Intelligence
سال: 2021
ISSN: 0162-8828,2160-9292,1939-3539
DOI: 10.1109/tpami.2021.3085858