arXiv research

New algorithm improves mean field inference in probabilistic models.

Paper proposes DG-ETC for online submodular maximization with stochastic bandit feedback.

Regularized greedy policies outperform classical greedy in finite-horizon bandit problems.

Greedy algorithm achieves sublinear regret for various distributions.

Greedy algorithm optimizes consumption habits with power utility.

New algorithms improve reinforcement learning with multi-step greedy policies.

Greedy policy achieves good results for adaptive submodular problems.

Greedy AutoAugment improves accuracy with less computation.

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 approach constructs efficient neural networks with ReLU.

Greedy coordinate descent achieves linear convergence for non-smooth composite problems.

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

Greedy policy maximizes information in unknown linear systems.

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…

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

New interactive greedy algorithm for group sparsity in high dimensions.

New algorithm speeds up learning of graphical models.

Paper improves greedy algorithm for non-submodular matroid constraints.

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

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.

New greedy algorithms improve Bayesian optimisation performance.

Greedy training of recursive partitioning estimators faces a computational barrier when the true function doesn't satisfy a specific property.

In this paper we consider the task of estimating the non-zero pattern of the sparse inverse covariance matrix of a zero-mean Gaussian random vector from a set of iid samples. Note that this is also equivalent to recovering the underlying graph structure of a sparse Gaussian Markov Random Field (GMRF). We present two no…

Greedy method adds neurons one by one for better function approximation.

Breathing k-means outperforms greedy k-means++ in clustering.

The paper gives a systematic study of the approximate versions of three greedy-type algorithms that are widely used in convex optimization. By approximate version we mean the one where some of evaluations are made with an error. Importance of such versions of greedy-type algorithms in convex optimization and in approxi…

Greedy algorithm performs well in online matching despite non-i.i.d. connections.

We consider interactive learning and covering problems, in a setting where actions may incur different costs, depending on the response to the action. We propose a natural greedy algorithm for response-dependent costs. We bound the approximation factor of this greedy algorithm in active learning settings as well as in …

Study on rapid policy changes in reinforcement learning.

This paper considers a recently emerged hyperspectral unmixing formulation based on sparse regression of a self-dictionary multiple measurement vector (SD-MMV) model, wherein the measured hyperspectral pixels are used as the dictionary. Operating under the pure pixel assumption, this SD-MMV formalism is special in that…

Differentiable Greedy Networks improve sentence selection for claim verification.

Greedy algorithms outperform UCB in many-armed bandit problems.

Greedy algorithms are widely used for problems in machine learning such as feature selection and set function optimization. Unfortunately, for large datasets, the running time of even greedy algorithms can be quite high. This is because for each greedy step we need to refit a model or calculate a function using the pre…

Greedy convex combination of models outperforms baselines.

Greedy policies perform poorly in imperfectly observed contextual bandits.

This paper analyzes the sample complexity of two timescale reinforcement learning algorithms.

NGP selects N features from P using neural networks in a greedy, iterative process.

We provide new approximation guarantees for greedy low rank matrix estimation under standard assumptions of restricted strong convexity and smoothness. Our novel analysis also uncovers previously unknown connections between the low rank estimation and combinatorial optimization, so much so that our bounds are reminisce…

Combines soft greediness with Modified Policy Iteration for more efficient deep reinforcement learning.

Large-scale L1-regularized loss minimization problems arise in high-dimensional applications such as compressed sensing and high-dimensional supervised learning, including classification and regression problems. High-performance algorithms and implementations are critical to efficiently solving these problems. Building…

Transforms offline greedy algorithms to online algorithms for combinatorial problems.

This work improves RLHF performance guarantees using greedy sampling.

We study the problem of selecting a subset of k random variables from a large set, in order to obtain the best linear prediction of another variable of interest. This problem can be viewed in the context of both feature selection and sparse approximation. We analyze the performance of widely used greedy heuristics, usi…