# Online Subset Selection using $\alpha$-Core with no Augmented Regret

@inproceedings{Sahoo2022OnlineSS, title={Online Subset Selection using \$\alpha\$-Core with no Augmented Regret}, author={Sourav Sahoo and Samrat Mukhopadhyay and Abhishek Sinha}, year={2022} }

We consider the problem of sequential sparse subset selections in an online learning setup. Assume that the set [ N ] consists of N distinct elements. On the t th round, a monotone reward function f t : 2 [ N ] → R + , which assigns a non-negative reward to each subset of [ N ] , is revealed to a learner. The learner selects (perhaps randomly) a subset S t ⊆ [ N ] of k elements before the reward function f t for that round is revealed ( k ≤ N ) . As a consequence of its choice, the learner…

## References

SHOWING 1-10 OF 54 REFERENCES

### k-experts - Online Policies and Fundamental Limits

- Computer ScienceAISTATS
- 2022

A tight regret lower bound is published for a variant of the k -experts problem, a generalization of the classic Prediction with Expert’s Advice framework, and the mistake bounds achievable by online learning policies for stable loss functions are characterized.

### An Optimal Learning Algorithm for Online Unconstrained Submodular Maximization

- Computer ScienceCOLT
- 2018

A polynomial-time no2 -regret algorithm for the online unconstrained submodular maximization problem, and an explicit subroutine for the two-experts problem that has an unusually strong regret guarantee.

### Non-Stochastic Bandit Slate Problems

- Computer ScienceNIPS
- 2010

We consider bandit problems, motivated by applications in online advertising and news story selection, in which the learner must repeatedly select a slate, that is, a subset of size s from K possible…

### Online Sparse Linear Regression

- Computer ScienceCOLT
- 2016

This work considers the online sparse linear regression problem, which is the problem of sequentially making predictions observing only a limited number of features in each round, to minimize regret with respect to the best sparse linear regressor, and gives an inefficient algorithm that obtains regret bounded by $\tilde{O}(\sqrt{T})$ after $T$ prediction rounds.

### Online Learning with Imperfect Hints

- Computer ScienceICML
- 2020

Algorithms and nearly matching lower bounds for online learning with imperfect directional hints are developed that are oblivious to the quality of the hints, and the regret bounds interpolate between the always-correlated hints case and the no-hints case.

### Online Learning of Assignments that Maximize Submodular Functions

- Computer ScienceArXiv
- 2009

This work presents an efficient algorithm for this general problem of ad allocation with submodular utilities and analyzes it in the no-regret model, demonstrating strong theoretical guarantees and empirically evaluating it on two real-world online optimization problems on the web.

### Greedy Minimization of Weakly Supermodular Set Functions

- Computer Science, MathematicsAPPROX-RANDOM
- 2017

This paper defines weak-$\alpha-supermodularity for set functions and gives new bicriteria results for $k$-means, sparse regression, and columns subset selection.

### An improved approximation algorithm for the column subset selection problem

- Mathematics, Computer ScienceSODA
- 2009

A novel two-stage algorithm that runs in O(min{mn2, m2n}) time and returns as output an m x k matrix C consisting of exactly k columns of A, and it is proved that the spectral norm bound improves upon the best previously-existing result and is roughly O(√k!) better than the best previous algorithmic result.

### LeadCache: Regret-Optimal Caching in Networks

- Computer Science
- 2020

This paper proposes LeadCache an online caching policy based on the Follow-the-Perturbed-Leader paradigm, and shows that the policy is regret-optimal up to a factor of Õ(n), where n is the number of users.

### Efficient learning algorithms for changing environments

- Computer ScienceICML '09
- 2009

A different performance metric is proposed which strengthens the standard metric of regret and measures performance with respect to a changing comparator and can be applied to various learning scenarios, i.e. online portfolio selection, for which there are experimental results showing the advantage of adaptivity.