arXiv research

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

TVBO optimizes time-varying functions with asymptotically vanishing regret.

In this paper, we formalise order-robust optimisation as an instance of online learning minimising simple regret, and propose Vroom, a zero'th order optimisation algorithm capable of achieving vanishing regret in non-stationary environments, while recovering favorable rates under stochastic reward-generating processes.…

New bandit algorithms focus on extreme values, outperforming existing methods.

New rule reduces exploration regret to logarithmic, improving bad episode handling.

Bayesian optimization method for permutations accelerates combinatorial search.

The paper tackles robust policy learning from multiple data sources.

New algorithm reduces bandit regret to log^3(T).

No-regret optimization for time-varying functions using uncertainty injection.

The problem of forecasting conditional probabilities of the next event given the past is considered in a general probabilistic setting. Given an arbitrary (large, uncountable) set C of predictors, we would like to construct a single predictor that performs asymptotically as well as the best predictor in C, on any data.…

We consider online optimization in the 1-lookahead setting, where the objective does not decompose additively over the rounds of the online game. The resulting formulation enables us to deal with non-stationary and/or long-term constraints , which arise, for example, in online display advertising problems. We propose a…

New algorithm reduces regret in noisy context bandits.

This paper analyses the problem of Gaussian process (GP) bandits with deterministic observations. The analysis uses a branch and bound algorithm that is related to the UCB algorithm of (Srinivas et al., 2010). For GPs with Gaussian observation noise, with variance strictly greater than zero, (Srinivas et al., 2010) pro…

This paper analyzes the problem of Gaussian process (GP) bandits with deterministic observations. The analysis uses a branch and bound algorithm that is related to the UCB algorithm of (Srinivas et al, 2010). For GPs with Gaussian observation noise, with variance strictly greater than zero, Srinivas et al proved that t…

New algorithm for contextual bandits with linear constraints using regression.

New algorithms reduce matching regret by limiting frequent updates.

New study reveals a polynomial penalty for adapting to unknown margin parameters in batched nonparametric bandits.

Gaussian prior and likelihood improve bandit learning performance.

New algorithm reduces regret for kernelized bandits by adapting to specific problem instances.

New model tackles interference in online experiments.

New algorithm for fair ranking in contextual bandits with concave rewards.

RONM method reduces regret in stochastic convex bandits with decreasing noise.

New algorithm improves cache management with delayed feedback and decaying costs.

New algorithm reduces sample complexity for Top Two method.

New algorithm identifies best arm in rested bandit setting.

New algorithm robust to probabilistic unbounded adversarial attacks in bandit problems.

Transformers solve Poisson means estimation via empirical Bayes.

LaMBO optimizes modular systems with switching costs, achieving better results than existing methods.

SRNNs achieve LSTMs' online regression performance in less time.

Study on newsvendor problem with censored data, showing how much information is lost.

New model considers unfairness complaints to ensure multiple fairness criteria.

A new sequential method estimates Poisson means in streaming data, achieving optimality and efficiency.

Regret minimization is treated as the golden rule in the traditional study of online learning. However, regret minimization algorithms tend to converge to the static optimum, thus being suboptimal for changing environments. To address this limitation, new performance measures, including dynamic regret and adaptive regr…

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…

Bandit algorithms struggle with consistent performance and robustness.