Melding the data-decisions pipeline: Decision-focused learning for combinatorial optimization
Creating impact in real-world settings requires artificial intelligence techniques to span the
full pipeline from data, to predictive models, to decisions. These components are typically …
full pipeline from data, to predictive models, to decisions. These components are typically …
Overparameterized nonlinear learning: Gradient descent takes the shortest path?
S Oymak, M Soltanolkotabi - International Conference on …, 2019 - proceedings.mlr.press
Many modern learning tasks involve fitting nonlinear models which are trained in an
overparameterized regime where the parameters of the model exceed the size of the …
overparameterized regime where the parameters of the model exceed the size of the …
Group-fairness in influence maximization
Influence maximization is a widely used model for information dissemination in social
networks. Recent work has employed such interventions across a wide range of social …
networks. Recent work has employed such interventions across a wide range of social …
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 …
Restricted strong convexity implies weak submodularity
We connect high-dimensional subset selection and submodular maximization. Our results
extend the work of Das and Kempe [In ICML (2011) 1057–1064] from the setting of linear …
extend the work of Das and Kempe [In ICML (2011) 1057–1064] from the setting of linear …
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 …
One sample stochastic frank-wolfe
One of the beauties of the projected gradient descent method lies in its rather simple
mechanism and yet stable behavior with inexact, stochastic gradients, which has led to its …
mechanism and yet stable behavior with inexact, stochastic gradients, which has led to its …
Online continuous submodular maximization
In this paper, we consider an online optimization process, where the objective functions are
not convex (nor concave) but instead belong to a broad class of continuous submodular …
not convex (nor concave) but instead belong to a broad class of continuous submodular …
Submodular reinforcement learning
In reinforcement learning (RL), rewards of states are typically considered additive, and
following the Markov assumption, they are $\textit {independent} $ of states visited …
following the Markov assumption, they are $\textit {independent} $ of states visited …
Resolving the approximability of offline and online non-monotone dr-submodular maximization over general convex sets
L Mualem, M Feldman - International Conference on Artificial …, 2023 - proceedings.mlr.press
In recent years, maximization of DR-submodular continuous functions became an important
research field, with many real-worlds applications in the domains of machine learning …
research field, with many real-worlds applications in the domains of machine learning …