In this paper, we aim to reveal the property, which makes the bandit combinatorial optimization hard. Recently, Cohen et al.~\citep{cohen2017tight} obtained a lower bound $\Omega(\sqrt{d k^3 T / \log T})$ of the regret, where $k$ is the maximum $\ell_1$-norm of action vectors, and $T$ is the number of rounds. This lower bound was achieved by considering a continuous strongly-correlated distribution of losses. Our main contribution is that we managed to improve this bound by $\Omega( \sqrt{d k ^3 T})$ through applying a factor of $\sqrt{\log T}$, which can be done by means of strongly-correlated losses with \textit{binary} values. The bound derives better regret bounds for three specific examples of the bandit combinatorial optimization: the multitask bandit, the bandit ranking and the multiple-play bandit. In particular, the bound obtained for the bandit ranking in the present study addresses an open problem raised in \citep{cohen2017tight}. In addition, we demonstrate that the problem becomes easier without considering correlations among entries of loss vectors. In fact, if each entry of loss vectors is an independent random variable, then, one can achieve a regret of $\tilde{O}(\sqrt{d k^2 T})$, which is $\sqrt{k}$ times smaller than the lower bound shown above. The observed results indicated that correlation among losses is the reason for observing a large regret.

We address the problem of sequential prediction with expert advice in a non-stationary environment with long-term memory guarantees in the sense of Bousquet and Warmuth [4]. We give a linear-time algorithm that improves on the best known regret bound [27]. This algorithm incorporates a relative entropy projection step. This projection is advantageous over previous weight-sharing approaches in that weight updates may come with implicit costs as in for example portfolio optimization. We give an algorithm to compute this projection step in linear time, which may be of independent interest.

In this work we consider a variant of adversarial online learning where in each round one picks $B$ out of $N$ arms and incurs cost equal to the $\textit{minimum}$ of the costs of each arm chosen. We propose an algorithm called Follow the Perturbed Multiple Leaders (FPML) for this problem, which we show (by adapting the techniques of Kalai and Vempala [2005]) achieves expected regret $\mathcal{O}(T^{\frac{1}{B+1}}\ln(N)^{\frac{B}{B+1}})$ over time horizon $T$ relative to the $\textit{single}$ best arm in hindsight. This introduces a trade-off between the budget $B$ and the single-best-arm regret, and we proceed to investigate several applications of this trade-off. First, we observe that algorithms which use standard regret minimizers as subroutines can sometimes be adapted by replacing these subroutines with FPML, and we use this to generalize existing algorithms for Online Submodular Function Maximization [Streeter and Golovin, 2008] in both the full feedback and semi-bandit feedback settings. Next, we empirically evaluate our new algorithms on an online black-box hyperparameter optimization problem. Finally, we show how FPML can lead to new algorithms for Linear Programming which require stronger oracles at the benefit of fewer oracle calls.

Stochastic and adversarial data are two widely studied settings in online learning. But many optimizationtasks are neither i.i.d.

Neural Information Processing Systems http://nips.cc/

We study an online learning problem where, over $T$ rounds, a learner observes both time-varying sets of feasible actions and an agent's optimal actions, selected by solving linear optimization over the feasible actions. The learner sequentially makes predictions of the agent's underlying linear objective function, and their quality is measured by the regret, the cumulative gap between optimal objective values and those achieved by following the learner's predictions. A seminal work by B\"armann et al. (ICML 2017) showed that online learning methods can be applied to this problem to achieve regret bounds of $O(\sqrt{T})$. Recently, Besbes et al. (COLT 2021, Oper. Res. 2023) significantly improved the result by achieving an $O(n^4\ln T)$ regret bound, where $n$ is the dimension of the ambient space of objective vectors. Their method, based on the ellipsoid method, runs in polynomial time but is inefficient for large $n$ and $T$. In this paper, we obtain an $O(n\ln T)$ regret bound, improving upon the previous bound of $O(n^4\ln T)$ by a factor of $n^3$. Our method is simple and efficient: we apply the online Newton step (ONS) to appropriate exp-concave loss functions. Moreover, for the case where the agent's actions are possibly suboptimal, we establish an $O(n\ln T+\sqrt{\Delta_Tn\ln T})$ regret bound, where $\Delta_T$ is the cumulative suboptimality of the agent's actions. This bound is achieved by using MetaGrad, which runs ONS with $\Theta(\ln T)$ different learning rates in parallel. We also provide a simple instance that implies an $\Omega(n)$ lower bound, showing that our $O(n\ln T)$ bound is tight up to an $O(\ln T)$ factor. This gives rise to a natural question: can the $O(\ln T)$ factor in the upper bound be removed? For the special case of $n=2$, we show that an $O(1)$ regret bound is possible, while we delineate challenges in extending this result to higher dimensions.

In particular, the gap in the analysis is due to my mis-reading the formula, and the response convinced me. However, the paper overall looks incremental, so it is a paper nice to have, but its acceptance seems to be depending on the quality of other papers.] The paper studies the bandit combinatorial optimization problem and improve the lower bound of the problem from \Omega(\sqrt{dk 3T/log T}) in the prior work [8] to \Omega(\sqrt{dk 3T}), removing a factor of 1/\sqrt{\log T} . This makes the regret dependency on T and k, d tight up to a logarithmic factor. The analysis is built upon prior work [2,8], with the major innovation being a design of new distribution of loss vectors (given in Eq.(8)) that leads to a better lower bound.

The reviewers all agree that this is a fine result.

The paper makes some interesting contribution by proposal a new partial information relaxation to improve the regret bound. The analysis of the partial info relaxation bears some similarity to that in Rahklin and Sridharan, but the inclusion of the Radamacher term is new. By using Lemma 2, the bound is improved. While this is definitely a new result and there are new ideas, the similarity to current literature kind of compels me to give a '3' instead of a '4' for the Novelty/Originality and Technical Constribution scores. Presentation: The paper is concise and well written, but I think that the proof of admissability between 5 and 7 is too "straight-lined".

Bayesian optimization (BO) with Gaussian process (GP) surrogate models is a powerful black-box optimization method. Acquisition functions are a critical part of a BO algorithm as they determine how the new samples are selected. Some of the most widely used acquisition functions include upper confidence bound (UCB) and Thompson sampling (TS). The convergence analysis of BO algorithms has focused on the cumulative regret under both the Bayesian and frequentist settings for the objective. In this paper, we establish new pointwise bounds on the prediction error of GP under the frequentist setting with Gaussian noise. Consequently, we prove improved convergence rates of cumulative regret bound for both GP-UCB and GP-TS. Of note, the new prediction error bound under Gaussian noise can be applied to general BO algorithms and convergence analysis, e.g., the asymptotic convergence of expected improvement (EI) with noise.