论文检索

Miscellaneous Aspects of Machine Learning/Online Learning, Active Learning and Bandits

Masoud Moravej Khorasani, Erik Weyer

Upper Confidence Bound (UCB) methods are one of the most effective methods in dealing with the exploration-exploitation trade-off in online decision-making problems. The confidence bounds utilized in UCB methods tend to be constructed based on concentration equalities which are usually dependent on a parameter of scale (e.g. a bound on the payoffs, a variance, or a subgaussian parameter) that must be known in advance. The necessity of knowing a scale parameter a priori and the fact that the confidence bounds only use the tail information can deteriorate the performance of the UCB methods.Here we propose a data-dependent UCB algorithm called MARS (Maximum Average Randomly Sampled) in a non-parametric setup for multi-armed bandits with symmetric rewards. The algorithm does not depend on any scaling, and the data-dependent upper confidence bound is constructed based on the maximum average of randomly sampled rewards inspired by the work of Hartigan in the 1960s and 70s. A regret bound for the multi-armed bandit problem is derived under the same assumptions as for the $\psi$-UCB method without incorporating any correction factors. The method is illustrated and compared with baseline algorithms in numerical experiments.

Miscellaneous Aspects of Machine Learning/Online Learning, Active Learning and Bandits

Banghua Zhu, Ying Sheng, Lianmin Zheng, Clark Barrett, Michael Jordan, Jiantao Jiao

Large Language Models (LLMs) and other large foundation models have achieved impressive results, but their size exacerbates existing resource consumption and latency challenges. In particular, the large-scale deployment of these models is hindered by the significant resource requirements during inference. In this paper, we study two approaches for mitigating these challenges: employing a cache to store previous queries and learning a model selector to choose from an ensemble of models for query processing.Theoretically, we provide an optimal algorithm for jointly optimizing both approaches to reduce the inference cost in both offline and online tabular settings. By combining a caching algorithm, namely Greedy Dual Size with Frequency (GDSF) or Least Expected Cost (LEC), with a model selector, we achieve optimal rates in both offline and online settings. Empirically, simulations show that our caching and model selection algorithm greatly improves over the baselines, with up to $50\times$ improvement over the baseline when the ratio between the maximum cost and minimum cost is $100$. Experiments on real datasets show a $4.3\times$ improvement in FLOPs over the baseline when the ratio for FLOPs is $10$, and a $1.8\times$ improvement in latency when the ratio for average latency is $1.85$.

Theory/Online Learning and Bandits

Filippo Vannella, Alexandre Proutiere, Jaeseong Jeong

We study the problem of regret minimization in Multi-Agent Multi-Armed Bandits (MAMABs) where the rewards are defined through a factor graph. We derive an instance-specific regret lower bound and characterize the minimal expected number of times each global action should be explored. Unfortunately, this bound and the corresponding optimal exploration process are obtained by solving a combinatorial optimization problem with a set of variables and constraints exponentially growing with the number of agents. We approximate the regret lower bound problem via Mean Field techniques to reduce the number of variables and constraints. By tuning the latter, we explore the trade-off between achievable regret and complexity. We devise Efficient Sampling for MAMAB (ESM), an algorithm whose regret asymptotically matches the corresponding approximated lower bound. We assess the regret and computational complexity of ESM numerically, using both synthetic and real-world experiments in radio communications networks.

Reinforcement Learning/Multi-agent

Soumyabrata Pal, Arun Suggala, Karthikeyan Shanmugam, Prateek Jain

We consider the problem of \emph{blocked} collaborative bandits where there are multiple users, each with an associated multi-armed bandit problem. These users are grouped into \emph{latent} clusters such that the mean reward vectors of users within the same cluster are identical. Our goal is to design algorithms that maximize the cumulative reward accrued by all the users over time, under the \emph{constraint} that no arm of a user is pulled more than $\mathsf{B}$ times. This problem has been originally considered by \cite{Bresler:2014}, and designing regret-optimal algorithms for it has since remained an open problem.In this work, we propose an algorithm called B-LATTICE (Blocked Latent bAndiTs via maTrIx ComplEtion) that collaborates across users, while simultaneously satisfying the budget constraints, to maximize their cumulative rewards. Theoretically, under certain reasonable assumptions on the latent structure, with $\mathsf{M}$ users, $\mathsf{N}$ arms, $\mathsf{T}$ rounds per user, and $\mathsf{C}=O(1)$ latent clusters, B-LATTICE achieves a per-user regret of $\widetilde{O}(\sqrt{\mathsf{T}(1 + \mathsf{N}\mathsf{M}^{-1})})$ under a budget constraint of $\mathsf{B}=\Theta(\log \mathsf{T})$. These are the first sub-linear regret bounds for this problem, and match the minimax regret bounds when $\mathsf{B}=\mathsf{T}$. Empirically, we demonstrate that our algorithm has superior performance over baselines even when $\mathsf{B}=1$. B-LATTICE is a phased algorithm where in each phase it clusters users into groups and collaborates across users within a group to quickly learn their reward models.

Miscellaneous Aspects of Machine Learning/Online Learning, Active Learning and Bandits

Yu-Jie Zhang, Zhen-Yu Zhang, Peng Zhao, Masashi Sugiyama

Dealing with distribution shifts is one of the central challenges for modern machine learning. One fundamental situation is the covariate shift, where the input distributions of data change from the training to testing stages while the input-conditional output distribution remains unchanged. In this paper, we initiate the study of a more challenging scenario --- continuous covariate shift --- in which the test data appear sequentially, and their distributions can shift continuously. Our goal is to adaptively train the predictor such that its prediction risk accumulated over time can be minimized. Starting with the importance-weighted learning, we theoretically show the method works effectively if the time-varying density ratios of test and train inputs can be accurately estimated. However, existing density ratio estimation methods would fail due to data scarcity at each time step. To this end, we propose an online density ratio estimation method that can appropriately reuse historical information. Our method is proven to perform well by enjoying a dynamic regret bound, which finally leads to an excess risk guarantee for the predictor. Empirical results also validate the effectiveness.

Miscellaneous Aspects of Machine Learning/Online Learning, Active Learning and Bandits

Parnian Kassraie, Nicolas Emmenegger, Andreas Krause, Aldo Pacchiano

Model selection in the context of bandit optimization is a challenging problem, as it requires balancing exploration and exploitation not only for action selection, but also for model selection. One natural approach is to rely on online learning algorithms that treat different models as experts. Existing methods, however, scale poorly ($\mathrm{poly}M$) with the number of models $M$ in terms of their regret.Our key insight is that, for model selection in linear bandits, we can emulate full-information feedback to the online learner with a favorable bias-variance trade-off. This allows us to develop ALEXP, which has an exponentially improved ($\log M$) dependence on $M$ for its regret.ALEXP has anytime guarantees on its regret, and neither requires knowledge of the horizon $n$, nor relies on an initial purely exploratory stage.Our approach utilizes a novel time-uniform analysis of the Lasso, establishing a new connection between online learning and high-dimensional statistics.

Theory/Online Learning and Bandits

Steve Hanneke, Shay Moran, Jonathan Shafer

We present new upper and lower bounds on the number of learner mistakes in the `transductive' online learning setting of Ben-David, Kushilevitz and Mansour (1997). This setting is similar to standard online learning, except that the adversary fixes a sequence of instances $x_1,\dots,x_n$ to be labeled at the start of the game, and this sequence is known to the learner. Qualitatively, we prove a \emph{trichotomy}, stating that the minimal number of mistakes made by the learner as $n$ grows can take only one of precisely three possible values: $n$, $\Theta\left(\log (n)\right)$, or $\Theta(1)$. Furthermore, this behavior is determined by a combination of the VC dimension and the Littlestone dimension. Quantitatively, we show a variety of bounds relating the number of mistakes to well-known combinatorial dimensions. In particular, we improve the known lower bound on the constant in the $\Theta(1)$ case from $\Omega\left(\sqrt{\log(d)}\right)$ to $\Omega(\log(d))$ where $d$ is the Littlestone dimension. Finally, we extend our results to cover multiclass classification and the agnostic setting.

Theory/Online Learning and Bandits

Hamish Flynn, David Reeb, Melih Kandemir, Jan Peters

We present improved algorithms with worst-case regret guarantees for the stochastic linear bandit problem. The widely used "optimism in the face of uncertainty" principle reduces a stochastic bandit problem to the construction of a confidence sequence for the unknown reward function. The performance of the resulting bandit algorithm depends on the size of the confidence sequence, with smaller confidence sets yielding better empirical performance and stronger regret guarantees. In this work, we use a novel tail bound for adaptive martingale mixtures to construct confidence sequences which are suitable for stochastic bandits. These confidence sequences allow for efficient action selection via convex programming. We prove that a linear bandit algorithm based on our confidence sequences is guaranteed to achieve competitive worst-case regret. We show that our confidence sequences are tighter than competitors, both empirically and theoretically. Finally, we demonstrate that our tighter confidence sequences give improved performance in several hyperparameter tuning tasks.

Miscellaneous Aspects of Machine Learning/Online Learning, Active Learning and Bandits

Omid Sadeghi, Maryam Fazel

We study a generalization of the online binary prediction with expert advice framework where at each round, the learner is allowed to pick $m\geq 1$ experts from a pool of $K$ experts and the overall utility is a modular or submodular function of the chosen experts. We focus on the setting in which experts act strategically and aim to maximize their influence on the algorithm's predictions by potentially misreporting their beliefs about the events. Among others, this setting finds applications in forecasting competitions where the learner seeks not only to make predictions by aggregating different forecasters but also to rank them according to their relative performance. Our goal is to design algorithms that satisfy the following two requirements: 1) \emph{Incentive-compatible}: Incentivize the experts to report their beliefs truthfully, and 2) \emph{No-regret}: Achieve sublinear regret with respect to the true beliefs of the best fixed set of $m$ experts in hindsight. Prior works have studied this framework when $m=1$ and provided incentive-compatible no-regret algorithms for the problem. We first show that a simple reduction of our problem to the $m=1$ setting is neither efficient nor effective. Then, we provide algorithms that utilize the specific structure of the utility functions to achieve the two desired goals.

Theory/Online Learning and Bandits

Hao Qin, Kwang-Sung Jun, Chicheng Zhang

We study $K$-armed bandit problems where the reward distributions of the arms are all supported on the $[0,1]$ interval. Maillard sampling\cite{maillard13apprentissage}, an attractive alternative to Thompson sampling, has recently been shown to achieve competitive regret guarantees in the sub-Gaussian reward setting\cite{bian2022maillard} while maintaining closed-form action probabilities, which is useful for offline policy evaluation. In this work, we analyze the Kullback-Leibler Maillard Sampling (KL-MS) algorithm, a natural extension of Maillard sampling {and a special case of Minimum Empirical Divergence (MED)~\cite{honda2011asymptotically}} for achieving a KL-style finite-time gap-dependent regret bound. We show that KL-MS enjoys the asymptotic optimality when the rewards are Bernoulli and has an {adaptive} worst-case regret bound of the form $O(\sqrt{\mu^*(1-\mu^*) K T \ln K} + K \ln T)$, where $\mu^*$ is the expected reward of the optimal arm, and $T$ is the time horizon length; {this is the first time such adaptivity is reported in the literature for an algorithm with asymptotic optimality guarantees.}

Theory/Online Learning and Bandits

Joe Suk, Samory Kpotufe

We study nonparametric contextual bandits where Lipschitz mean reward functions may change over time.We first establish the minimax dynamic regret rate in this less understood setting in terms of number of changes $L$ and total-variation $V$, both capturing all changes in distribution over context space, and argue that state-of-the-art procedures are suboptimal in this setting.Next, we tend to the question of an _adaptivity_ for this setting, i.e. achieving the minimax rate without knowledge of $L$ or $V$. Quite importantly, we posit that the bandit problem, viewed locally at a given context $X_t$, should not be affected by reward changes in other parts of context space $\cal X$. We therefore propose a notion of _change_, which we term _experienced significant shifts_, that better accounts for locality, and thus counts considerably less changes than $L$ and $V$. Furthermore, similar to recent work on non-stationary MAB (Suk & Kpotufe, 2022), _experienced significant shifts_ only count the most _significant_ changes in mean rewards, e.g., severe best-arm changes relevant to observed contexts.Our main result is to show that this more tolerant notion of change can in fact be adapted to.

Theory/Online Learning and Bandits

Osama Hanna, Lin Yang, Christina Fragouli

In this paper, we provide the first efficient batched algorithm for contextual linear bandits with large action spaces. Unlike existing batched algorithms that rely on action elimination, which are not implementable for large action sets, our algorithm only uses a linear optimization oracle over the action set to design the policy. The proposed algorithm achieves a regret upper bound $\tilde{O}(\sqrt{T})$ with high probability, and uses $O(\log\log T)$ batches, matching the lower bound on the number of batches (Gao et al., 2019). When specialized to linear bandits, our algorithm can achieve a high probability gap-dependent regret bound of $\tilde{O}(1/\Delta_{\min})$ with the optimal $\log T$ number of batches, where $\Delta_{\min}$ is the minimum reward gap between a suboptimal arm and the optimal. Our result is achieved via a novel soft elimination approach, that entails $\text{``}$shaping$\text{"}$ the action sets at each batch so that we can efficiently identify (near) optimal actions.

Theory/Online Learning and Bandits

Kiarash Banihashem, MohammadTaghi Hajiaghayi, Suho Shin, Max Springer

We present an oracle-efficient relaxation for the adversarial contextual bandits problem, where the contexts are sequentially drawn i.i.d from a known distribution and the cost sequence is chosen by an online adversary. Our algorithm has a regret bound of $O(T^{\frac{2}{3}}(K\log(|\Pi|))^{\frac{1}{3}})$ and makes at most $O(K)$ calls per round to an offline optimization oracle, where $K$ denotes the number of actions, $T$ denotes the number of rounds and $\Pi$ denotes the set of policies. This is the first result to improve the prior best bound of $O((TK)^{\frac{2}{3}}(\log(|\Pi|))^{\frac{1}{3}})$ as obtained by Syrgkanis et al. at NeurIPS 2016, and the first to match the original bound of Langford and Zhang at NeurIPS 2007 which was obtained for the stochastic case.

Theory/Reinforcement Learning and Planning

Dylan J Foster, Noah Golowich, Jian Qian, Alexander Rakhlin, Ayush Sekhari

We consider the problem of interactive decision making, encompassing structured bandits and reinforcementlearning with general function approximation. Recently, Foster et al. (2021) introduced theDecision-Estimation Coefficient, a measure of statistical complexity that lower bounds the optimal regret for interactive decisionmaking, as well as a meta-algorithm, Estimation-to-Decisions, which achieves upperbounds in terms of the same quantity. Estimation-to-Decisions is a reduction, which liftsalgorithms for (supervised) online estimation into algorithms fordecision making. In this paper, we show that by combining Estimation-to-Decisions witha specialized form of "optimistic" estimation introduced byZhang (2022), it is possible to obtain guaranteesthat improve upon those of Foster et al. (2021) byaccommodating more lenient notions of estimation error. We use this approach to derive regret bounds formodel-free reinforcement learning with value function approximation, and give structural results showing when it can and cannot help more generally.

Theory/Online Learning and Bandits

Qining Zhang, Lei Ying

This paper considers a stochastic Multi-Armed Bandit (MAB) problem with dual objectives: (i) quick identification and commitment to the optimal arm, and (ii) reward maximization throughout a sequence of $T$ consecutive rounds. Though each objective has been individually well-studied, i.e., best arm identification for (i) and regret minimization for (ii), the simultaneous realization of both objectives remains an open problem, despite its practical importance. This paper introduces \emph{Regret Optimal Best Arm Identification} (ROBAI) which aims to achieve these dual objectives. To solve ROBAI with both pre-determined stopping time and adaptive stopping time requirements, we present an algorithm called EOCP and its variants respectively, which not only achieve asymptotic optimal regret in both Gaussian and general bandits, but also commit to the optimal arm in $\mathcal{O}(\log T)$ rounds with pre-determined stopping time and $\mathcal{O}(\log^2 T)$ rounds with adaptive stopping time. We further characterize lower bounds on the commitment time (equivalent to the sample complexity) of ROBAI, showing that EOCP and its variants are sample optimal with pre-determined stopping time, and almost sample optimal with adaptive stopping time. Numerical results confirm our theoretical analysis and reveal an interesting ``over-exploration'' phenomenon carried by classic UCB algorithms, such that EOCP has smaller regret even though it stops exploration much earlier than UCB, i.e., $\mathcal{O}(\log T)$ versus $\mathcal{O}(T)$, which suggests over-exploration is unnecessary and potentially harmful to system performance.

Theory/Online Learning and Bandits

Dairui Wang, Junyu Cao, Yan Zhang, Wei Qi

Delayed feedback is a critical problem in dynamic recommender systems. In practice, the feedback result often depends on the frequency of recommendation. Most existing online learning literature fails to consider optimization of the recommendation frequency, and regards the reward from each successfully recommended message to be equal. In this paper, we consider a novel cascading bandits setting, where individual messages from a selected list are sent to a user periodically. Whenever a user does not like a message, she may abandon the system with a probability positively correlated with the recommendation frequency. A learning agent needs to learn both the underlying message attraction probabilities and users' abandonment probabilities through the randomly delayed feedback. We first show a dynamic programming solution to finding the optimal message sequence in deterministic scenarios, in which the reward is allowed to vary with different messages. Then we propose a polynomial time UCB-based offline learning algorithm, and discuss its performance by characterizing its regret bound. For the online setting, we propose a learning algorithm which allows adaptive content for a given user. Numerical experiment on AmEx dataset confirms the effectiveness of our algorithms.

Theory/Online Learning and Bandits

Li Fan, Ruida Zhou, Chao Tian, Cong Shen

We study a federated linear bandits model, where $M$ clients communicate with a central server to solve a linear contextual bandits problem with finite adversarial action sets that may be different across clients. To address the unique challenges of **adversarial finite** action sets, we propose the FedSupLinUCB algorithm, which extends the principles of SupLinUCB and OFUL algorithms in linear contextual bandits. We prove that FedSupLinUCB achieves a total regret of $\tilde{O}(\sqrt{d T})$, where $T$ is the total number of arm pulls from all clients, and $d$ is the ambient dimension of the linear model. This matches the minimax lower bound and thus is order-optimal (up to polylog terms). We study both asynchronous and synchronous cases and show that the communication cost can be controlled as $O(d M^2 \log(d)\log(T))$ and $O(\sqrt{d^3 M^3} \log(d))$, respectively. The FedSupLinUCB design is further extended to two scenarios: (1) variance-adaptive, where a total regret of $\tilde{O} (\sqrt{d \sum \nolimits_{t=1}^{T} \sigma_t^2})$ can be achieved with $\sigma_t^2$ being the noise variance of round $t$; and (2) adversarial corruption, where a total regret of $\tilde{O}(\sqrt{dT} + d C_p)$ can be achieved with $C_p$ being the total corruption budget. Experiment results corroborate the theoretical analysis and demonstrate the effectiveness of \alg on both synthetic and real-world datasets.

Theory/Online Learning and Bandits

Zhepei Wei, Chuanhao Li, Haifeng Xu, Hongning Wang

Most existing works on federated bandits take it for granted that all clients are altruistic about sharing their data with the server for the collective good whenever needed. Despite their compelling theoretical guarantee on performance and communication efficiency, this assumption is overly idealistic and oftentimes violated in practice, especially when the algorithm is operated over self-interested clients, who are reluctant to share data without explicit benefits. Negligence of such self-interested behaviors can significantly affect the learning efficiency and even the practical operability of federated bandit learning. In light of this, we aim to spark new insights into this under-explored research area by formally introducing an incentivized communication problem for federated bandits, where the server shall motivate clients to share data by providing incentives. Without loss of generality, we instantiate this bandit problem with the contextual linear setting and propose the first incentivized communication protocol, namely, Inc-FedUCB, that achieves near-optimal regret with provable communication and incentive cost guarantees. Extensive empirical experiments on both synthetic and real-world datasets further validate the effectiveness of the proposed method across various environments.

Miscellaneous Aspects of Machine Learning/Online Learning, Active Learning and Bandits

Yu-Hu Yan, Peng Zhao, Zhi-Hua Zhou

In this paper, we propose an online convex optimization approach with two different levels of adaptivity. On a higher level, our approach is agnostic to the unknown types and curvatures of the online functions, while at a lower level, it can exploit the unknown niceness of the environments and attain problem-dependent guarantees. Specifically, we obtain $\mathcal{O}(\log V_T)$, $\mathcal{O}(d \log V_T)$ and $\hat{\mathcal{O}}(\sqrt{V_T})$ regret bounds for strongly convex, exp-concave and convex loss functions, respectively, where $d$ is the dimension, $V_T$ denotes problem-dependent gradient variations and the $\hat{\mathcal{O}}(\cdot)$-notation omits $\log V_T$ factors. Our result not only safeguards the worst-case guarantees but also directly implies the small-loss bounds in analysis. Moreover, when applied to adversarial/stochastic convex optimization and game theory problems, our result enhances the existing universal guarantees. Our approach is based on a multi-layer online ensemble framework incorporating novel ingredients, including a carefully designed optimism for unifying diverse function types and cascaded corrections for algorithmic stability. Notably, despite its multi-layer structure, our algorithm necessitates only one gradient query per round, making it favorable when the gradient evaluation is time-consuming. This is facilitated by a novel regret decomposition equipped with carefully designed surrogate losses.