Stochastic conditional gradient methods: From convex minimization to submodular maximization
This paper considers stochastic optimization problems for a large class of objective
functions, including convex and continuous submodular. Stochastic proximal gradient …
functions, including convex and continuous submodular. Stochastic proximal gradient …
Submodular maximization beyond non-negativity: Guarantees, fast algorithms, and applications
It is generally believed that submodular functions–and the more general class of $\gamma $-
weakly submodular functions–may only be optimized under the non-negativity assumption …
weakly submodular functions–may only be optimized under the non-negativity assumption …
On acceleration with noise-corrupted gradients
M Cohen, J Diakonikolas… - … Conference on Machine …, 2018 - proceedings.mlr.press
Accelerated algorithms have broad applications in large-scale optimization, due to their
generality and fast convergence. However, their stability in the practical setting of noise …
generality and fast convergence. However, their stability in the practical setting of noise …
Continuous dr-submodular maximization: Structure and algorithms
DR-submodular continuous functions are important objectives with wide real-world
applications spanning MAP inference in determinantal point processes (DPPs), and mean …
applications spanning MAP inference in determinantal point processes (DPPs), and mean …
Deterministic algorithms for submodular maximization problems
N Buchbinder, M Feldman - ACM Transactions on Algorithms (TALG), 2018 - dl.acm.org
Randomization is a fundamental tool used in many theoretical and practical areas of
computer science. We study here the role of randomization in the area of submodular …
computer science. We study here the role of randomization in the area of submodular …
The approximate duality gap technique: A unified theory of first-order methods
J Diakonikolas, L Orecchia - SIAM Journal on Optimization, 2019 - SIAM
We present a general technique for the analysis of first-order methods. The technique relies
on the construction of a duality gap for an appropriate approximation of the objective …
on the construction of a duality gap for an appropriate approximation of the objective …
Constrained submodular maximization via new bounds for dr-submodular functions
N Buchbinder, M Feldman - Proceedings of the 56th Annual ACM …, 2024 - dl.acm.org
Submodular maximization under various constraints is a fundamental problem studied
continuously, in both computer science and operations research, since the late 1970's. A …
continuously, in both computer science and operations research, since the late 1970's. A …
Greed is good: Near-optimal submodular maximization via greedy optimization
It is known that greedy methods perform well for maximizing\textitmonotone submodular
functions. At the same time, such methods perform poorly in the face of non-monotonicity. In …
functions. At the same time, such methods perform poorly in the face of non-monotonicity. In …
Constrained submodular maximization via a nonsymmetric technique
N Buchbinder, M Feldman - Mathematics of Operations …, 2019 - pubsonline.informs.org
The study of combinatorial optimization problems with submodular objectives has attracted
much attention in recent years. Such problems are important in both theory and practice …
much attention in recent years. Such problems are important in both theory and practice …
Do less, get more: Streaming submodular maximization with subsampling
In this paper, we develop the first one-pass streaming algorithm for submodular
maximization that does not evaluate the entire stream even once. By carefully subsampling …
maximization that does not evaluate the entire stream even once. By carefully subsampling …