Online Continuous DR-Submodular Maximization with Long-Term Budget Constraints

In this paper, we study a class of online optimization problems with long-term budget constraints where the objective functions are not necessarily concave (nor convex) but they instead satisfy the Diminishing Returns (DR) property. Specifically, a sequence of monotone DR-submodular objective functions $\{f_t(x)\}_{t=1}^T$ and monotone linear budget functions $\{\langle p_t,x \rangle \}_{t=1}^T$ arrive over time and assuming a total targeted budget $B_T$, the goal is to choose points $x_t$ at each time $t\in\{1,\dots,T\}$, without knowing $f_t$ and $p_t$ on that step, to achieve sub-linear regret bound while the total budget violation $\sum_{t=1}^T \langle p_t,x_t \rangle -B_T$ is sub-linear as well. Prior work has shown that achieving sub-linear regret is impossible if the budget functions are chosen adversarially. Therefore, we modify the notion of regret by comparing the agent against a $(1-\frac{1}{e})$-approximation to the best fixed decision in hindsight which satisfies the budget constraint proportionally over any window of length $W$. We propose the Online Saddle Point Hybrid Gradient (OSPHG) algorithm to solve this class of online problems. For $W=T$, we recover the aforementioned impossibility result. However, when $W=o(T)$, we show that it is possible to obtain sub-linear bounds for both the $(1-\frac{1}{e})$-regret and the total budget violation.

[1]  Qing Ling,et al.  An Online Convex Optimization Approach to Proactive Network Resource Allocation , 2017, IEEE Transactions on Signal Processing.

[2]  Maryam Fazel,et al.  Competitive online algorithms for resource allocation over the positive semidefinite cone , 2018, Mathematical Programming.

[3]  Hao Yu,et al.  Online Convex Optimization with Time-Varying Constraints , 2017, 1702.04783.

[4]  Elad Hazan,et al.  Introduction to Online Convex Optimization , 2016, Found. Trends Optim..

[5]  Cédric Archambeau,et al.  Adaptive Algorithms for Online Convex Optimization with Long-term Constraints , 2015, ICML.

[6]  D K Smith,et al.  Numerical Optimization , 2001, J. Oper. Res. Soc..

[7]  Maryam Fazel,et al.  Designing smoothing functions for improved worst-case competitive ratio in online optimization , 2016, NIPS.

[8]  Ashish Kapoor,et al.  Safety-Aware Algorithms for Adversarial Contextual Bandit , 2017, ICML.

[9]  K. J. Ray Liu,et al.  Online Convex Optimization With Time-Varying Constraints and Bandit Feedback , 2019, IEEE Transactions on Automatic Control.

[10]  Jan Vondrák,et al.  Maximizing a Submodular Set Function Subject to a Matroid Constraint (Extended Abstract) , 2007, IPCO.

[11]  Andreas Krause,et al.  Online Submodular Maximization under a Matroid Constraint with Application to Learning Assignments , 2014, ArXiv.

[12]  Andreas Krause,et al.  Guaranteed Non-convex Optimization: Submodular Maximization over Continuous Domains , 2016, AISTATS.

[13]  Jan Vondrák,et al.  Optimal approximation for the submodular welfare problem in the value oracle model , 2008, STOC.

[14]  Andreas Krause,et al.  Optimal Continuous DR-Submodular Maximization and Applications to Provable Mean Field Inference , 2019, ICML.

[15]  Amin Karbasi,et al.  Projection-Free Online Optimization with Stochastic Gradient: From Convexity to Submodularity , 2018, ICML.

[16]  Rong Jin,et al.  Trading regret for efficiency: online convex optimization with long term constraints , 2011, J. Mach. Learn. Res..

[17]  Thrasyvoulos Spyropoulos,et al.  Cautious Regret Minimization: Online Optimization with Long-Term Budget Constraints , 2019, ICML.

[18]  John N. Tsitsiklis,et al.  Online Learning with Sample Path Constraints , 2009, J. Mach. Learn. Res..

[19]  Jianjun Yuan,et al.  Online Convex Optimization for Cumulative Constraints , 2018, NeurIPS.

[20]  Rishabh K. Iyer,et al.  Monotone Closure of Relaxed Constraints in Submodular Optimization: Connections Between Minimization and Maximization , 2014, UAI.

[21]  Andreas Krause,et al.  Optimal DR-Submodular Maximization and Applications to Provable Mean Field Inference , 2018, ICML 2019.

[22]  Andreas Krause,et al.  Submodular Function Maximization , 2014, Tractability.

[23]  Amin Karbasi,et al.  Online Continuous Submodular Maximization , 2018, AISTATS.

[24]  Andreas Krause,et al.  Continuous DR-submodular Maximization: Structure and Algorithms , 2017, NIPS 2017.