arXiv research

A new method for learning to defer decisions with expert advice improves over standard methods.

Advice-efficient prediction with expert advice (in analogy to label-efficient prediction) is a variant of prediction with expert advice game, where on each round of the game we are allowed to ask for advice of a limited number $M$ out of $N$ experts. This setting is especially interesting when asking for advice of ever…

Conventional learning with expert advice methods assumes a learner is always receiving the outcome (e.g., class labels) of every incoming training instance at the end of each trial. In real applications, acquiring the outcome from oracle can be costly or time consuming. In this paper, we address a new problem of active…

Investigates fast prediction rates with limited expert advice.

Study finds optimal regret bound for multi-armed bandit problem with expert advice.

A simple algorithm improves model generalization in expert advice settings.

Improved regret bounds for bandits with expert advice.

Improved regret bounds for bandits with fixed expert advice using information theory.

Improves reward bounds for prediction with expert advice using abstention.

A new framework uses deep RL to aggregate expert advice for better portfolio management.

Improved algorithm reduces regret in corrupted expert advice setting.

A key challenge in online learning is that classical algorithms can be slow to adapt to changing environments. Recent studies have proposed "meta" algorithms that convert any online learning algorithm to one that is adaptive to changing environments, where the adaptivity is analyzed in a quantity called the strongly-ad…

New algorithms improve prediction with expert advice under local differential privacy.

New algorithm reduces expert prediction regret for two experts.

We prove non-asymptotic lower bounds on the expectation of the maximum of $d$ independent Gaussian variables and the expectation of the maximum of $d$ independent symmetric random walks. Both lower bounds recover the optimal leading constant in the limit. A simple application of the lower bound for random walks is an (…

Paper studies continuous prediction with experts' advice using differential equations.

We provide the first algorithm for online bandit linear optimization whose regret after T rounds is of order sqrt{Td ln N} on any finite class X of N actions in d dimensions, and of order d*sqrt{T} (up to log factors) when X is infinite. These bounds are not improvable in general. The basic idea utilizes tools from con…

Bayesian algorithms improve online learning with adversaries over infinite action spaces.

In the framework of prediction with expert advice, we consider a recently introduced kind of regret bounds: the bounds that depend on the effective instead of nominal number of experts. In contrast to the Normal- Hedge bound, which mainly depends on the effective number of experts but also weakly depends on the nominal…

Sharp bounds found on expert error in binary advice aggregation.

Novel algorithms for online learning with uncertain feedback graphs reduce regret.

Generalized algorithm for translation and scale-invariant prediction.

This work addresses the classic machine learning problem of online prediction with expert advice. We consider the finite-horizon version of this zero-sum, two-person game. Using verification arguments from optimal control theory, we view the task of finding better lower and upper bounds on the value of the game (regret…

With the increasing volume of data in the world, the best approach for learning from this data is to exploit an online learning algorithm. Online ensemble methods are online algorithms which take advantage of an ensemble of classifiers to predict labels of data. Prediction with expert advice is a well-studied problem i…

This work addresses the classic machine learning problem of online prediction with expert advice. A new potential-based framework for the fixed horizon version of this problem has been recently developed using verification arguments from optimal control theory. This paper extends this framework to the random (geometric…

Survey of algorithms to correct past mistakes in prediction.

We consider an original problem that arises from the issue of security analysis of a power system and that we name optimal discovery with probabilistic expert advice. We address it with an algorithm based on the optimistic paradigm and on the Good-Turing missing mass estimator. We prove two different regret bounds on t…

New algorithms reduce label collection for online prediction with expert advice.

New algorithm improves bandit with graph feedback by decomposing regret.

Improved prediction algorithm for 'easy' sequences with reduced regret.

The paper tackles online learning with two types of losses and shows it's impossible without certain assumptions.

For the prediction with experts' advice setting, we construct forecasting algorithms that suffer loss not much more than any expert in the pool. In contrast to the standard approach, we investigate the case of long-term forecasting of time series and consider two scenarios. In the first one, at each step $t$ the learne…

We study the multiclass online learning problem where a forecaster makes a sequence of predictions using the advice of $n$ experts. Our main contribution is to analyze the regime where the best expert makes at most $b$ mistakes and to show that when $b = o(\log_4{n})$, the expected number of mistakes made by the optima…

New algorithms reduce private bandit regret to nearly non-private levels.

This paper introduces a novel optimization method for differential neural architecture search, based on the theory of prediction with expert advice. Its optimization criterion is well fitted for an architecture-selection, i.e., it minimizes the regret incurred by a sub-optimal selection of operations. Unlike previous s…

The paper extends a prediction method to curved spaces.

Improved cumulative regret for sequence prediction with limited expert advice.

Study on a new family of problems interpolating expert advice and multi-armed bandits.

Efficiently optimizes boolean functions using multilinear polynomials and exponential weight updates.

We consider a variation on the problem of prediction with expert advice, where new forecasters that were unknown until then may appear at each round. As often in prediction with expert advice, designing an algorithm that achieves near-optimal regret guarantees is straightforward, using aggregation of experts. However, …

The paper explores trade-offs between regret and variance in online learning algorithms.

Online prediction improves with abstention, reducing regret to a fixed bound.

A novel algorithm for actively trading stocks is presented. While traditional expert advice and "universal" algorithms (as well as standard technical trading heuristics) attempt to predict winners or trends, our approach relies on predictable statistical relations between all pairs of stocks in the market. Our empirica…

Active learning aims to reduce annotation cost by predicting which samples are useful for a human teacher to label. However it has become clear there is no best active learning algorithm. Inspired by various philosophies about what constitutes a good criteria, different algorithms perform well on different datasets. Th…

The paper shows optimal robustness against adversarial corruption in sequential decision-making problems.

We investigate the adversarial bandit problem with multiple plays under semi-bandit feedback. We introduce a highly efficient algorithm that asymptotically achieves the performance of the best switching $m$-arm strategy with minimax optimal regret bounds. To construct our algorithm, we introduce a new expert advice alg…

Meta-algorithm optimizes nonstochastic bandits with infinitely many experts.

We study the relationship between the notions of differentially private learning and online learning in games. Several recent works have shown that differentially private learning implies online learning, but an open problem of Neel, Roth, and Wu \cite{NeelAaronRoth2018} asks whether this implication is {\it efficient}…