arXiv research

New analysis shows Thompson Sampling can work with greedy approximations in combinatorial bandits.

Study improves CTS's approximation regret for combinatorial bandits.

Often times, in many design problems, there is a need to select a small set of informative or representative elements from a large ground set of entities in an optimal fashion. Submodular optimization that provides for a formal way to solve such problems, has recently received significant attention from the controls co…

The paper explores MAB strategies for very short horizons, introducing new methods and showing improved performance.

New algorithm maximizes non-monotone adaptive submodular functions in linear time.

In this paper, we propose to combine imitation and reinforcement learning via the idea of reward shaping using an oracle. We study the effectiveness of the near-optimal cost-to-go oracle on the planning horizon and demonstrate that the cost-to-go oracle shortens the learner's planning horizon as function of its accurac…

GPE algorithm optimizes nonparametric contextual bandits with efficient regret bounds.

New algorithm finds k-centers from noisy distance estimates.

Assessing the predictive accuracy of black box classifiers is challenging in the absence of labeled test datasets. In these scenarios we may need to rely on a human oracle to evaluate individual predictions; presenting the challenge to create query algorithms to guide the search for points that provide the most informa…

Given a finite family of functions, the goal of model selection aggregation is to construct a procedure that mimics the function from this family that is the closest to an unknown regression function. More precisely, we consider a general regression model with fixed design and measure the distance between functions by …

The paper tackles fast rates in batch active learning with pool-based data.

New framework tackles stochastic latent subgroup heterogeneity in online decision-making.

This paper is about variable selection, clustering and estimation in an unsupervised high-dimensional setting. Our approach is based on fitting constrained Gaussian mixture models, where we learn the number of clusters $K$ and the set of relevant variables $S$ using a generalized Bayesian posterior with a sparsity indu…

Algorithm approximates target distribution using weight queries.

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…

This work explores adaptations of successful multi-armed bandits policies to the online contextual bandits scenario with binary rewards using binary classification algorithms such as logistic regression as black-box oracles. Some of these adaptations are achieved through bootstrapping or approximate bootstrapping, whil…

The paper optimizes A/B tests by balancing lift and cost in large-scale settings.

Efficient algorithms for planning in cooperative multi-agent reinforcement learning with combinatorial action spaces.

New PCstar algorithm discovers causal structure of max-linear Bayesian networks.

New framework for resilient bi-criteria optimization under noisy feedback.

We propose a novel active learning framework for activity recognition using wearable sensors. Our work is unique in that it takes physical and cognitive limitations of the oracle into account when selecting sensor data to be annotated by the oracle. Our approach is inspired by human-beings' limited capacity to respond …

New algorithm converges to equilibrium in nonconvex-nonconcave optimization problems without dimension dependence.

Study when to replace machine learning models with new data.

New method improves Bayesian optimization by considering budget and prior quality.

A new method for dynamic feature selection outperforms existing approaches.

Contextual bandit algorithms are essential for solving many real-world interactive machine learning problems. Despite multiple recent successes on statistically and computationally efficient methods, the practical behavior of these algorithms is still poorly understood. We leverage the availability of large numbers of …

New framework tackles submodular welfare with multi-agent combinatorial bandits.

Greedy algorithm achieves sublinear regret for various distributions.

Greedy algorithm optimizes consumption habits with power utility.

We present an information-theoretic framework for sequential adaptive compressed sensing, Info-Greedy Sensing, where measurements are chosen to maximize the extracted information conditioned on the previous measurements. We show that the widely used bisection approach is Info-Greedy for a family of $k$-sparse signals b…

New distributions allow greedy arm selection in sparse bandit problems.

Simpler ε-greedy with longer action durations improves exploration.

This paper is a follow up to the previous author's paper on convex optimization. In that paper we began the process of adjusting greedy-type algorithms from nonlinear approximation for finding sparse solutions of convex optimization problems. We modified there three the most popular in nonlinear approximation in Banach…

Introduces greedy feature selection for classifier-dependent feature ranking.

Greedy policy maximizes information in unknown linear systems.

Greedy selection works well in a toy model of independent increments.

This paper proposes and evaluates the k-greedy equivalence search algorithm (KES) for learning Bayesian networks (BNs) from complete data. The main characteristic of KES is that it allows a trade-off between greediness and randomness, thus exploring different good local optima. When greediness is set at maximum, KES co…

Oracle-efficient algorithms reduce combinatorial semi-bandit regret to logarithmic time.

Multiple-step lookahead policies have demonstrated high empirical competence in Reinforcement Learning, via the use of Monte Carlo Tree Search or Model Predictive Control. In a recent work \cite{efroni2018beyond}, multiple-step greedy policies and their use in vanilla Policy Iteration algorithms were proposed and analy…

Paper analyzes Greedy-GQ for reinforcement learning with Markovian noise.

New algorithm speeds up learning of graphical models.

FIGS improves prediction performance while maintaining interpretability, especially in medical domains.

Improved greedy 2-coordinate updates for optimization problems with constraints.

We propose a new concept named adaptive submodularity ratio to study the greedy policy for sequential decision making. While the greedy policy is known to perform well for a wide variety of adaptive stochastic optimization problems in practice, its theoretical properties have been analyzed only for a limited class of p…

New algorithms sample convex bodies using Markov chains and restricted Gaussian oracles.

The contextual bandit literature has traditionally focused on algorithms that address the exploration-exploitation tradeoff. In particular, greedy algorithms that exploit current estimates without any exploration may be sub-optimal in general. However, exploration-free greedy algorithms are desirable in practical setti…

Greedy algorithm nearly outperforms exploration in contextual bandits.

MAMBA learns policies competitive with multiple conflicting oracles.