Online Learning

Meta-learning is characterized by its ability to learn how to learn, enabling the adaptation of learning strategies across different tasks. Recent research introduced the Meta-Thompson Sampling (Meta-TS), which meta-learns an unknown prior distribution sampled from a meta-prior by interacting with bandit instances drawn from it. However, its analysis was limited to Gaussian bandit. The contextual multi-armed bandit framework is an extension of the Gaussian Bandit, which challenges agent to utili...

This paper studies two variants of the best arm identification (BAI) problem under the streaming model, where we have a stream of $n$ arms with reward distributions supported on $[0,1]$ with unknown means. The arms in the stream are arriving one by one, and the algorithm cannot access an arm unless it is stored in a limited size memory. We first study the streaming \eps-$top$-$k$ arms identification problem, which asks for $k$ arms whose reward means are lower than that of the $k$-th best arm ...

In real-world streaming recommender systems, user preferences often dynamically change over time (e.g., a user may have different preferences during weekdays and weekends). Existing bandit-based streaming recommendation models only consider time as a timestamp, without explicitly modeling the relationship between time variables and time-varying user preferences. This leads to recommendation models that cannot quickly adapt to dynamic scenarios. To address this issue, we propose a contextual band...

We study online learning in episodic finite-horizon Markov decision processes (MDPs) with convex objective functions, known as the concave utility reinforcement learning (CURL) problem. This setting generalizes RL from linear to convex losses on the state-action distribution induced by the agent's policy. The non-linearity of CURL invalidates classical Bellman equations and requires new algorithmic approaches. We introduce the first algorithm achieving near-optimal regret bounds for online CURL ...

In this paper, we investigate the streaming bandits problem, wherein the learner aims to minimize regret by dealing with online arriving arms and sublinear arm memory. We establish the tight worst-case regret lower bound of $Ω\left( (TB)^α K^{1-α}\right), α= 2^{B} / (2^{B+1}-1)$ for any algorithm with a time horizon $T$, number of arms $K$, and number of passes $B$. The result reveals a separation between the stochastic bandits problem in the classical centralized setting and the streaming setti...

Regret minimization in streaming multi-armed bandits (MABs) has been studied extensively in recent years. In the single-pass setting with $K$ arms and $T$ trials, a regret lower bound of $Ω(T^{2/3})$ has been proved for any algorithm with $o(K)$ memory (Maiti et al. [NeurIPS'21]; Agarwal at al. [COLT'22]). On the other hand, however, the previous best regret upper bound is still $O(K^{1/3} T^{2/3}\log^{1/3}(T))$, which is achieved by the streaming implementation of the simple uniform exploration...

We study the problem of online clustering within the multi-armed bandit framework under the fixed confidence setting. In this multi-armed bandit problem, we have $M$ arms, each providing i.i.d. samples that follow a multivariate Gaussian distribution with an {\em unknown} mean and a known unit covariance. The arms are grouped into $K$ clusters based on the distance between their means using the Single Linkage (SLINK) clustering algorithm on the means of the arms. Since the true means are unknown...

We study reinforcement learning with linear function approximation and adversarially changing cost functions, a setup that has mostly been considered under simplifying assumptions such as full information feedback or exploratory conditions.We present a computationally efficient policy optimization algorithm for the challenging general setting of unknown dynamics and bandit feedback, featuring a combination of mirror-descent and least squares policy evaluation in an auxiliary MDP used to compute ...

We study high-dimensional multi-armed contextual bandits with batched feedback where the $T$ steps of online interactions are divided into $L$ batches. In specific, each batch collects data according to a policy that depends on previous batches and the rewards are revealed only at the end of the batch. Such a feedback structure is popular in applications such as personalized medicine and online advertisement, where the online data often do not arrive in a fully serial manner. We consider high-di...

We study linear bandits under exact sliding-window constraints, where every consecutive block of actions must belong to a prescribed feasible set. In the offline setting, where the reward function is known, we show that convexity and cyclic-shift invariance make a stationary solution optimal when $w\mid T$ and within an additive $O(w)$ gap otherwise. In the online setting, we show that geometric structure alone is insufficient for learning, and sublinear regret can be impossible. We introduce a ...

Online safe reinforcement learning (RL) plays a key role in dynamic environments, with applications in autonomous driving, robotics, and cybersecurity. The objective is to learn optimal policies that maximize rewards while satisfying safety constraints modeled by constrained Markov decision processes (CMDPs). Existing methods achieve sublinear regret under stochastic constraints but often fail in adversarial settings, where constraints are unknown, time-varying, and potentially adversarially des...

We study the generalized linear contextual bandit problem within the constraints of limited adaptivity. In this paper, we present two algorithms, $\texttt{B-GLinCB}$ and $\texttt{RS-GLinCB}$, that address, respectively, two prevalent limited adaptivity settings. Given a budget $M$ on the number of policy updates, in the first setting, the algorithm needs to decide upfront $M$ rounds at which it will update its policy, while in the second setting it can adaptively perform $M$ policy updates durin...

Online learning is a model of machine learning where the learner is trained on sequential feedback. We investigate worst-case error for the online learning of real functions that have certain smoothness constraints. Suppose that $\mathcal{F}_q$ is the class of all absolutely continuous functions $f: [0, 1] \rightarrow \mathbb{R}$ such that $\|f'\|_q \le 1$, and $\operatorname{opt}_p(\mathcal{F}_q)$ is the best possible upper bound on the sum of the $p^{\text{th}}$ powers of absolute prediction e...

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 o...

The contextual duelling bandit problem models adaptive recommender systems, where the algorithm presents a set of items to the user, and the user's choice reveals their preference. This setup is well suited for implicit choices users make when navigating a content platform, but does not capture other possible comparison queries. Motivated by the fact that users provide more reliable feedback after consuming items, we propose a new bandit model that can be described as follows. The algorithm reco...

We study online classification under smoothed adversaries. In this setting, at each time point, the adversary draws an example from a distribution that has a bounded density with respect to a fixed base measure, which is known apriori to the learner. For binary classification and scalar-valued regression, previous works \citep{haghtalab2020smoothed, block2022smoothed} have shown that smoothed online learning is as easy as learning in the iid batch setting under PAC model. However, we show that s...

We analyze the effect that online algorithms have on the environment that they are learning. As a motivation, consider recommendation systems that use online algorithms to learn optimal product recommendations based on user and product attributes. It is well known that the sequence of recommendations affects user preferences. However, typical learning algorithms treat the user attributes as static and disregard the impact of their recommendations on user preferences. Our interest is to analyze t...

The last decade has witnessed many successes of deep learning-based models for industry-scale recommender systems. These models are typically trained offline in a batch manner. While being effective in capturing users' past interactions with recommendation platforms, batch learning suffers from long model-update latency and is vulnerable to system biases, making it hard to adapt to distribution shift and explore new items or user interests. Although online learning-based approaches (e.g., multi-...

We study the generalized linear contextual bandit problem within the constraints of limited adaptivity. In this paper, we present two algorithms, $\texttt{B-GLinCB}$ and $\texttt{RS-GLinCB}$, that address, respectively, two prevalent limited adaptivity settings. Given a budget $M$ on the number of policy updates, in the first setting, the algorithm needs to decide upfront $M$ rounds at which it will update its policy, while in the second setting it can adaptively perform $M$ policy updates durin...

The contextual multi-armed bandit (MAB) problem is crucial in sequential decision-making. A line of research, known as online clustering of bandits, extends contextual MAB by grouping similar users into clusters, utilizing shared features to improve learning efficiency. However, existing algorithms, which rely on the upper confidence bound (UCB) strategy, struggle to gather adequate statistical information to accurately identify unknown user clusters. As a result, their theoretical analyses requ...