arXiv research

New algorithms reduce regret in both stochastic and deterministic environments.

New algorithm optimizes multi-armed bandit performance in stochastic and adversarial settings.

Improved regret bounds for contextual bandits considering variance sequences.

New algorithm reduces regret in infinite MDPs with optimal variance-dependent bounds.

New algorithms reduce regret in online MDPs by adapting to data and variance.

New algorithm reduces regret for linear bandits with unknown noise variance.

Improved online confidence bounds for multinomial logistic models in bandits.

A new batch ensemble method reduces regret in stochastic bandits.

Improved GP bandit algorithms for noiseless, varying noise, and RKHS norms.

Optimal strategy identified for minimizing regret in fixed-budget best arm selection.

FGTSVA improves Thompson Sampling for contextual bandits with optimal variance-aware regret.

We consider a sequential learning problem with Gaussian payoffs and side information: after selecting an action $i$, the learner receives information about the payoff of every action $j$ in the form of Gaussian observations whose mean is the same as the mean payoff, but the variance depends on the pair $(i,j)$ (and may…

Contextual bandits study how reward variance affects regret bounds.

Improved bounds for Monte Carlo Rademacher Averages using self-bounding functions.

Atlas-type models are constant-parameter models of uncorrelated stocks for equity markets with a stable capital distribution, in which the growth rates and variances depend on rank. The simplest such model assigns the same, constant variance to all stocks; zero rate of growth to all stocks but the smallest; and positiv…

Algorithm identifies best arm in bandit game with variance consideration.

The aim of this article is to design a moment transformation for Student- t distributed random variables, which is able to account for the error in the numerically computed mean. We employ Student-t process quadrature, an instance of Bayesian quadrature, which allows us to treat the integral itself as a random variable…

The proposed model modifies option pricing formulas for the basic case of log-normal probability distribution providing correspondence to formulated criteria of efficiency and completeness. The model is self-calibrating by historic volatility data; it maintains the constant expected value at maturity of the hedged inst…

The paper analyzes high-dimensional kernel regression, showing different risk curves based on data and regularization.

Improves active learning efficiency by warping input space based on observed outputs.

The relationship between the size and the variance of firm growth rates is known to follow an approximate power-law behavior $σ(S) \sim S^{-β(S)}$ where $S$ is the firm size and $β(S)\approx 0.2$ is an exponent weakly dependent on $S$. Here we show how a model of proportional growth which treats firms as classes compos…

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.

Multiplicative noise models are often used instead of additive noise models in cases in which the noise variance depends on the state. Furthermore, when Poisson distributions with relatively small counts are approximated with normal distributions, multiplicative noise approximations are straightforward to implement. Th…

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 …

New estimator accurately estimates mean of real-valued distributions without variance knowledge.

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.