More Like this

1. Randomized Greedy Learning for Non-monotone Stochastic Submodular Maximization Under Full-bandit Feedback

   Fourati, Fares ; Aggarwal, Vaneet ; Quinn, Christopher John ; Alouini, Mohamed-Slim ( April 2023 , Proceedings of the International Workshop on Artificial Intelligence and Statistics)

   We investigate the problem of unconstrained combinatorial multi-armed bandits with full-bandit feedback and stochastic rewards for submodular maximization. Previous works investigate the same problem assuming a submodular and monotone reward function. In this work, we study a more general problem, i.e., when the reward function is not necessarily monotone, and the submodularity is assumed only in expectation. We propose Randomized Greedy Learning (RGL) algorithm and theoretically prove that it achieves a $\frac{1}{2}$-regret upper bound of $\Tilde{\mathcal{O}}(n T^{\frac{2}{3}})$ for horizon $T$ and number of arms $n$. We also show in experiments that RGL empirically outperforms other full-bandit variants in submodular and non-submodular settings. 

   more » « less
2. Randomized Greedy Learning for Non-monotone Stochastic Submodular Maximization Under Full-bandit Feedback

   Fares Fourati, Vaneet Aggarwal ( January 2023 , Proceedings of Machine Learning Research)

   We investigate the problem of unconstrained combinatorial multi-armed bandits with fullbandit feedback and stochastic rewards for submodular maximization. Previous works investigate the same problem assuming a submodular and monotone reward function. In this work, we study a more general problem, i.e., when the reward function is not necessarily monotone, and the submodularity is assumed only in expectation. We propose Randomized Greedy Learning (RGL) algorithm and theoretically prove that it achieves a 1 2 -regret upper bound of O˜(nT 2 3 ) for horizon T and number of arms n. We also show in experiments that RGL empirically outperforms other full-bandit variants in submodular and non-submodular settings. 

   more » « less
3. On the Unreasonable Effectiveness of the Greedy Algorithm: Greedy Adapts to Sharpness

   Pokutta, S. ; Singh, M. ; Torrico, A. ( June 2020 , Thirty-seventh International Conference on Machine Learning)

   It is well known that the standard greedy algorithm guarantees a worst-case approximation factor of 1 − 1/e when maximizing a monotone submodular function under a cardinality constraint. However, empirical studies show that its performance is substantially better in practice. This raises a natural question of explaining this improved performance of the greedy algorithm. In this work, we define sharpness for submodular functions as a candidate explanation for this phenomenon. We show that the greedy algorithm provably performs better as the sharpness of the submodular function increases. This improvement ties in closely with the faster convergence rates of first order methods for sharp functions in convex optimization. 

   more » « less
4. Differentially Private Decomposable Submodular Maximization

   Chaturvedi, Anamay ; Nguyễn, Huy Lê ; Zakynthinou, Lydia ( May 2021 , Proceedings of the AAAI Conference on Artificial Intelligence)

   We study the problem of differentially private constrained maximization of decomposable submodular functions. A submodular function is decomposable if it takes the form of a sum of submodular functions. The special case of maximizing a monotone, decomposable submodular function under cardinality constraints is known as the Combinatorial Public Projects (CPP) problem (Papadimitriou, Schapira, and Singer 2008). Previous work by Gupta et al. (2010) gave a differentially private algorithm for the CPP problem. We extend this work by designing differentially private algorithms for both monotone and non-monotone decomposable submodular maximization under general matroid constraints, with competitive utility guarantees. We complement our theoretical bounds with experiments demonstrating improved empirical performance. 

   more » « less
5. Approximating Red-Blue Set Cover and Minimum Monotone Satisfying Assignment

   https://doi.org/10.4230/LIPIcs.APPROX/RANDOM.2023.11  

   Chlamtáč, Eden ; Makarychev, Yury ; Vakilian, Ali ( September 2023 , Approximation, Randomization, and Combinatorial Optimization. Algorithms and Techniques (APPROX/RANDOM 2023))

   Megow, Nicole ; Smith, Adam (Ed.)

   We provide new approximation algorithms for the Red-Blue Set Cover and Circuit Minimum Monotone Satisfying Assignment (MMSA) problems. Our algorithm for Red-Blue Set Cover achieves Õ(m^{1/3})-approximation improving on the Õ(m^{1/2})-approximation due to Elkin and Peleg (where m is the number of sets). Our approximation algorithm for MMSA_t (for circuits of depth t) gives an Õ(N^{1-δ}) approximation for δ = 1/3 2^{3-⌈t/2⌉}, where N is the number of gates and variables. No non-trivial approximation algorithms for MMSA_t with t ≥ 4 were previously known. We complement these results with lower bounds for these problems: For Red-Blue Set Cover, we provide a nearly approximation preserving reduction from Min k-Union that gives an Ω(m^{1/4 - ε}) hardness under the Dense-vs-Random conjecture, while for MMSA we sketch a proof that an SDP relaxation strengthened by Sherali-Adams has an integrality gap of N^{1-ε} where ε → 0 as the circuit depth t → ∞. 

   more » « less