arXiv research

The paper studies early stopping methods in linear contextual bandits.

Unified model optimizes experiment performance and reduces duration.

DTS improves robustness of bandit algorithms in nonstationary environments.

New method optimizes multiple objectives in A/B testing for AI and clinical trials.

Users in social networks whose posts stay at the top of their followers'{} feeds the longest time are more likely to be noticed. Can we design an online algorithm to help them decide when to post to stay at the top? In this paper, we address this question as a novel optimal control problem for jump stochastic different…

We conduct a large-scale, systematic study to evaluate the existing evaluation methods for natural language generation in the context of generating online product reviews. We compare human-based evaluators with a variety of automated evaluation procedures, including discriminative evaluators that measure how well machi…

In this paper, we study the design and analysis of experiments conducted on a set of units over multiple time periods where the starting time of the treatment may vary by unit. The design problem involves selecting an initial treatment time for each unit in order to most precisely estimate both the instantaneous and cu…

Paper proposes algorithms to minimize both dynamic and adaptive regret simultaneously.

Statistical inference for misspecified contextual bandits is challenging due to adaptivity issues.

The paper analyzes the sliding regret of stochastic bandit algorithms.

This paper analyzes regret bounds for Gaussian process Thompson sampling.

The notion of \emph{policy regret} in online learning is a well defined? performance measure for the common scenario of adaptive adversaries, which more traditional quantities such as external regret do not take into account. We revisit the notion of policy regret and first show that there are online learning settings …

Online learning algorithms are designed to learn even when their input is generated by an adversary. The widely-accepted formal definition of an online algorithm's ability to learn is the game-theoretic notion of regret. We argue that the standard definition of regret becomes inadequate if the adversary is allowed to a…

Balances the regret of different algorithms in bandit and RL problems.

Data-driven model selection reduces regret in sequential decisions.

Optimistic Hedge achieves optimal regret bounds in two-player zero-sum games.

We consider an online learning process to forecast a sequence of outcomes for nonconvex models. A typical measure to evaluate online learning algorithms is regret but such standard definition of regret is intractable for nonconvex models even in offline settings. Hence, gradient based definition of regrets are common f…

Optimal switching regret for all segmentations in online convex optimisation.

New approach for distributed online optimization of non-convex losses with sublinear regret.

Regret minimization is a powerful tool for solving large-scale problems; it was recently used in breakthrough results for large-scale extensive-form game solving. This was achieved by composing simplex regret minimizers into an overall regret-minimization framework for extensive-form game strategy spaces. In this paper…

New algorithm SELECT minimizes satisficing regret in bandits.

We study the Thompson sampling algorithm in an adversarial setting, specifically, for adversarial bit prediction. We characterize the bit sequences with the smallest and largest expected regret. Among sequences of length $T$ with $k < \frac{T}{2}$ zeros, the sequences of largest regret consist of alternating zeros and …

This paper considers the stability of online learning algorithms and its implications for learnability (bounded regret). We introduce a novel quantity called {\em forward regret} that intuitively measures how good an online learning algorithm is if it is allowed a one-step look-ahead into the future. We show that given…

Paper introduces a new $G^\star$ regret measure for online convex optimization with smooth losses.

Bandit algorithms struggle with consistent performance and robustness.

Paper improves worst-case regret bounds for RLSVI in reinforcement learning.

Paper solves no-swap regret minimization for combinatorial bandits with polylogarithmic dependence on N.

New algorithms reduce dynamic regret in non-stationary RL environments.

New algorithms minimize simple and cumulative regret in contextual bandits.

Paper explores rate-preserving reductions between Blackwell approachability and no-regret learning.

Algorithm minimizes regret and converges to equilibria in Markov games.

There are two variants of the classical multi-armed bandit (MAB) problem that have received considerable attention from machine learning researchers in recent years: contextual bandits and simple regret minimization. Contextual bandits are a sub-class of MABs where, at every time step, the learner has access to side in…

New algorithm achieves both static and dynamic regret optimally against an oblivious adversary for deterministic losses.

We consider regret minimization in repeated games with non-convex loss functions. Minimizing the standard notion of regret is computationally intractable. Thus, we define a natural notion of regret which permits efficient optimization and generalizes offline guarantees for convergence to an approximate local optimum. W…

New algorithm reduces regret from sqrt(T) to polylog(T) in stochastic contextual linear bandits.

In online learning, the dynamic regret metric chooses the reference (optimal) solution that may change over time, while the typical (static) regret metric assumes the reference solution to be constant over the whole time horizon. The dynamic regret metric is particularly interesting for applications such as online reco…

New algorithm reduces online learning regret in uninformed Markov games.

Study on individual regret in cooperative MAB with agents communicating over a graph.

Efficient algorithms for online learning with changing action sets, achieving no-approximate-regret guarantees.

No-regret learning with strategic experts, incentivized.

SCaLE tackles dynamic regret in noisy bandit feedback with switching costs.

Improved single-pass streaming MAB regret bound to O(K^1/3T^2/3).

We consider online learning problems where the aim is to achieve regret which is efficient in the sense that it is the same order as the lowest regret amongst K experts. This is a substantially stronger requirement that achieving $O(\sqrt{n})$ or $O(\log n)$ regret with respect to the best expert and standard algorithm…

We investigate online convex optimization in changing environments, and choose the adaptive regret as the performance measure. The goal is to achieve a small regret over every interval so that the comparator is allowed to change over time. Different from previous works that only utilize the convexity condition, this pa…

Study on Pareto optimality in multi-objective bandit problems.

The paper minimizes Borda regret in dueling bandits models.

Unified framework for distributional regret in bandits and reinforcement learning.

We establish linear regret bounds for convex smooth losses using Fenchel-Young losses.