On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,181 papers · 148 categories

Trend · papers per month

count % of corpus

48 results for “multiple-step greedy consistency”

Multiple-Step Greedy Policies in Online and Approximate Reinforcement Learningcs.LG

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

problem Difficulty in monotonic policy improvement with soft-policy updates.

method Formulated and analyzed online and approximate algorithms using multi-step greedy operators.

result Guaranteed monotonic policy improvement with sufficiently large update stepsize.

Reinforcement Learning Monte Carlo Tree Search Policy Iteration Soft Policy Multi-step Greedy

2018-05-21abs ↗pdf ↗

How to Combine Tree-Search Methods in Reinforcement Learningcs.LG

Enhances tree search methods in reinforcement learning for better convergence.

problem Non-contractive nature of standard tree search methods in reinforcement learning.

method Proposes a new method to back up values at the root using the optimal tree path return.

result Establishes a

γ^h

-contracting procedure leading to better convergence rates.

reinforcement learning tree search Monte Carlo Tree Search contracting procedure multiple-step greedy consistency

2018-09-06abs ↗pdf ↗

Beyond the One Step Greedy Approach in Reinforcement Learningcs.AI

New algorithms for reinforcement learning improve policy improvement with multiple steps.

problem Improving policies with multiple steps in reinforcement learning.

method Formulated and analyzed variants of multiple-step policy improvement, derived new algorithms, and proved their convergence.

result Recent reinforcement learning algorithms are instances of the proposed framework.

reinforcement learning policy improvement multiple steps convergence empirical success

2018-02-10abs ↗pdf ↗

Policy Mirror Descent with Lookaheadcs.LG

Enhances PMD with lookahead to improve RL performance.

problem Improving RL performance with greedy policies over 1-step.

method Integrates multi-step greedy policies into PMD with lookahead.

result Shows faster convergence rate for

h

-PMD.

Policy Mirror Descent Lookahead RL Convergence Rate Multi-step Greedy

2024-03-21abs ↗pdf ↗

Using quantile time series and historical simulation to forecast financial risk multiple steps aheadq-fin.ST

The paper develops a method to forecast financial risk multiple steps ahead using quantile time series and historical simulation.

problem Forecasting financial risk multiple steps ahead with accurate estimation of Value-at-Risk (VaR) and Expected Shortfall (ES).

method Quantile-based, semi-parametric historical simulation estimation of VaR and ES models, using quantile loss function and resampling.

result The proposed method accurately forecasts VaR and ES one and multiple steps ahead, superior to existing methods.

quantile time series historical simulation Value-at-Risk Expected Shortfall tail risk

2025-02-28abs ↗pdf ↗

An End-to-End Time Series Model for Simultaneous Imputation and Forecastcs.LG

Model predicts future values and fills in missing data.

problem Missing data in time series data.

method End-to-end time series model with two neural networks.

result Framework performs well in imputation and forecasting.

time series forecasting imputation neural networks missing data

2023-06-01abs ↗pdf ↗

The Greedy Advantage in Finite-Horizon Banditsstat.ML

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

problem Optimizing decision-making in sequential experiments with finite time constraints.

method Developed regularized greedy algorithms for multi-armed Bernoulli bandits.

result Calibrated regularized greedy policies consistently match or outperform state-of-the-art algorithms.

bandits greedy finite horizon regression sequential decision making

2026-07-31abs ↗pdf ↗

Greedy equivalence search for nonparametric graphical modelsstat.ML

GES algorithm improves consistency for nonparametric DAG models.

problem Consistent estimation of nonparametric DAG models.

method Greedy equivalence search with new consistency proof for nonparametric families.

result Consistency of GES for general nonparametric DAG models with smooth factorization.

graphical models nonparametric DAG consistency Bayes

2024-06-25abs ↗pdf ↗

A Retrospective Approximation Approach for Smooth Stochastic Optimizationmath.OC

A new approach RA improves stochastic optimization by executing multiple steps between subsample updates.

problem Improving the efficiency and effectiveness of stochastic optimization methods.

method Developed Retrospective Approximation (RA) which executes multiple steps between subsample updates using a deterministic solver.

result RA achieves almost sure and

L_1

consistency under weak conditions and optimizes iteration and oracle complexity.

stochastic optimization retrospective approximation deterministic solver stochastic gradient smooth objective

2021-03-07abs ↗pdf ↗

Forecast Network-Wide Traffic States for Multiple Steps Ahead: A Deep Learning Approach Considering Dynamic Non-Local Spatial Correlation and Non-Stationary Temporal Dependencycs.LG

Deep learning model predicts traffic flows across entire network for multiple steps ahead.

problem Accurately forecasting future traffic flows across all network links.

method Spatial-Temporal Sequence to Sequence (STSeq2Seq) model combining seq2seq and graph convolution.

result STSeq2Seq achieves state-of-the-art performance in traffic forecasting.

deep learning traffic forecasting spatial correlation temporal dependency sequence to sequence

2020-04-06abs ↗pdf ↗

Worst-case Performance of Greedy Policies in Bandits with Imperfect Context Observationsstat.ML

Greedy policies perform poorly in imperfectly observed contextual bandits.

problem Performance of Greedy policies in bandits with partially observed contexts.

method Analysis of Greedy reinforcement learning policies under imperfectly observed contextual bandits.

result Worst-case regret grows poly-logarithmically with the time horizon and the failure probability.

bandits contextual greedy policies imperfect observations regret analysis

2022-04-10abs ↗pdf ↗

Generative Adversarial Network for Probabilistic Forecast of Random Dynamical Systemcs.LG

Generative adversarial network for probabilistic forecasting of random systems.

problem Forecasting random dynamical systems without distributional assumptions.

method Recurrent neural network and generative adversarial network (GAN) with regularization based on maximum mean discrepancy (MMD).

result The proposed model successfully forecasts complex stochastic processes with multiple-step predictions.

deep learning probabilistic forecasting random dynamical systems GAN maximum mean discrepancy

2021-11-04abs ↗pdf ↗

Combined l_1 and greedy l_0 penalized least squares for linear model selectionstat.ML

We introduce a computationally effective algorithm for a linear model selection consisting of three steps: screening--ordering--selection (SOS). Screening of predictors is based on the thresholded Lasso that is l_1 penalized least squares. The screened predictors are then fitted using least squares (LS) and ordered wit…

2013-10-22abs ↗pdf ↗

Breathing K-Means: Superior K-Means Solutions through Dynamic K-Valuescs.LG

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

problem Improving k-means clustering solutions.

method Dynamic adjustment of centroids through breathing technique.

result Breathing k-means outperforms other k-means techniques, especially greedy k-means++.

k-means clustering centroid adjustment dynamic k-values clustering algorithms greedy k-means++

2020-06-28abs ↗pdf ↗

Partial Wasserstein Coveringcs.LG

Partial Wasserstein Covering aims to identify missing patterns in datasets.

problem Identifying missing patterns in datasets compared to actual applications.

method Formulated as a discrete optimization problem with partial Wasserstein divergence. Proved submodular, allowing greedy approximation. Proposed quasi-greedy algorithms with acceleration techniques.

result Efficiently fills gaps and finds missing scenes in real driving scenes datasets.

partial Wasserstein covering discrete optimization submodular property greedy algorithm quasi-greedy algorithms

2021-06-02abs ↗pdf ↗

High-dimensional Sparse Inverse Covariance Estimation using Greedy Methodscs.LG

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…

2011-12-29abs ↗pdf ↗

The Unreasonable Effectiveness of Greedy Algorithms in Multi-Armed Bandit with Many Armscs.LG

Greedy algorithms outperform UCB in many-armed bandit problems.

problem Optimizing multi-armed bandit problems with many arms.

method Subsampled UCB and greedy algorithms comparison.

result Greedy algorithms achieve optimal regret in many-armed bandit problems.

bandit problems many-armed greedy algorithms UCB subsampled

2020-02-24abs ↗pdf ↗

A Greedy PDE Router for Blending Neural Operators and Classical Methodsstat.ME

A new method combines classical and machine learning PDE solvers efficiently.

problem Combining classical and machine learning PDE solvers to reduce computational cost and improve accuracy.

method Proposes an approximate greedy router to select solvers at each iteration, mimicking a greedy approach.

result Consistently reduces final error and AUC of the error trajectory compared to single-solver baselines and hybrid approaches.

PDE solvers machine learning greedy algorithm combinatorial problem error reduction

2025-09-29abs ↗pdf ↗

ConQUR: Mitigating Delusional Bias in Deep Q-learningcs.LG

ConQUR tackles delusional bias in deep Q-learning, improving performance in Atari games.

problem Delusional bias in deep Q-learning.

method Efficient methods to mitigate delusional bias by training Q-approximators with consistent labels and a search framework.

result Improves performance in Atari games, sometimes dramatically.

deep Q-learning delusional bias consistent labels greedy policy penalization scheme

2020-02-27abs ↗pdf ↗

Greedy Deep Dictionary Learningcs.LG

In this work we propose a new deep learning tool called deep dictionary learning. Multi-level dictionaries are learnt in a greedy fashion, one layer at a time. This requires solving a simple (shallow) dictionary learning problem, the solution to this is well known. We apply the proposed technique on some benchmark deep…

2016-01-31abs ↗pdf ↗

Forward-Backward Greedy Algorithms for General Convex Smooth Functions over A Cardinality Constraintstat.ML

We consider forward-backward greedy algorithms for solving sparse feature selection problems with general convex smooth functions. A state-of-the-art greedy method, the Forward-Backward greedy algorithm (FoBa-obj) requires to solve a large number of optimization problems, thus it is not scalable for large-size problems…

2013-12-31abs ↗pdf ↗

Regret Minimization and Statistical Inference in Online Decision Making with High-dimensional Covariatescs.LG

Paper addresses regret minimization and inference in high-dimensional online decision-making.

problem Regret minimization and statistical inference in high-dimensional online decision-making.

method Integrates ε-greedy bandit algorithm with hard thresholding for sparse bandit parameters and debiasing method for inference.

result Achieves either

O(T^{1/2})

regret or

O(T^{1/2})

-consistent inference, with trade-off between exploration and exploitation.

regret minimization statistical inference online decision making high-dimensional covariates sparse linear context bandit

2024-11-10abs ↗pdf ↗

Partitioned hybrid learning of Bayesian network structuresstat.ML

Novel hybrid method for Bayesian network structure learning reduces computational time without sacrificing accuracy.

problem Bayesian network structure learning efficiency and accuracy trade-off.

method Partitioned PC (pPC),

p

-value adjacency thresholding (PATH), hybrid greedy initialization (HGI).

result pHGS achieves significant computational reductions compared to the PC algorithm without sacrificing structure learning accuracy.

Bayesian networks structure learning hybrid algorithms divide-and-conquer parameter tuning

2021-03-22abs ↗pdf ↗

Learning Powerful Policies by Using Consistent Dynamics Modelcs.LG

The paper proposes a method to improve reinforcement learning by ensuring consistency between observed and imagined dynamics.

problem Compounding errors in traditional model-based reinforcement learning approaches.

method An auxiliary cost function to ensure consistency between observed and imagined dynamics.

result The proposed approach helps train powerful policies and better dynamics models.

reinforcement learning model-based consistency dynamics interaction

2019-06-11abs ↗pdf ↗

Kernel

ε

-Greedy for Multi-Armed Bandits with Covariatesstat.ML

Kernel $ε$ -Greedy optimizes multi-armed bandits with covariates for sub-linear regret.

problem Optimizing multi-armed bandits with covariates in a reproducing kernel Hilbert space.

method Online weighted kernel ridge regression estimator for mean reward function estimation.

result Achieves sub-linear regret rate and optimal

\sqrt{T}

regret rate under margin condition.

multi-armed bandits covariates kernel ridge regression reproducing kernel Hilbert space sub-linear regret

2023-06-29abs ↗pdf ↗

A Greedy Algorithm to Cluster Specialistscs.LG

Several recent deep neural networks experiments leverage the generalist-specialist paradigm for classification. However, no formal study compared the performance of different clustering algorithms for class assignment. In this paper we perform such a study, suggest slight modifications to the clustering procedures, and…

2016-09-13abs ↗pdf ↗

The Greedy Miser: Learning under Test-time Budgetscs.LG

As machine learning algorithms enter applications in industrial settings, there is increased interest in controlling their cpu-time during testing. The cpu-time consists of the running time of the algorithm and the extraction time of the features. The latter can vary drastically when the feature set is diverse. In this…

2012-06-27abs ↗pdf ↗

A multivariate water quality parameter prediction model using recurrent neural networkcs.LG

Research develops a water quality prediction model using LSTM.

problem Global degradation of water resources and need for optimal water quality monitoring.

method Developed a multivariate water quality prediction model using LSTM and historical data.

result Multiple step LSTM model achieved RMSE of 0.227 mg/L.

water quality water resources recurrent neural network LSTM water management

2020-03-25abs ↗pdf ↗

Recurrent Convolution for Compact and Cost-Adjustable Neural Networks: An Empirical Studycs.CV

RC reduces neural network redundancy and improves performance through independent BN layers.

problem Improving neural network performance and reducing redundancy.

method Recurrent convolution with independent batch normalization layers for different unrolling steps.

result The proposed method improves RC networks' performance and achieves cost-adjustable inference.

Recurrent Convolution Neural Networks Batch Normalization Model Compression Cost-Adjustable Inference

2019-02-26abs ↗pdf ↗

Extremely Greedy Equivalence Searchcs.LG

XGES improves GES by favoring early edge deletion, outperforming GES in finite data settings.

problem Learning directed acyclic graphs from finite data.

method Extremely Greedy Equivalent Search (XGES) improves GES by favoring early edge deletion.

result XGES consistently outperforms GES in recovering the correct graphs, and is 10 times faster.

causal discovery equivalence search greedy search finite data local optima

2025-02-26abs ↗pdf ↗

Federated Learning with Unbiased Gradient Aggregation and Controllable Meta Updatingcs.LG

Federated learning improves by unbiased gradient aggregation and controllable meta updating.

problem Gradient biases and inconsistency between target and optimization objectives in federated averaging.

method Unbiased gradient aggregation with keep-trace gradient descent and gradient evaluation strategy, controllable meta updating with small data samples.

result Faster convergence and higher accuracy with different network architectures in various FL settings.

federated learning gradient aggregation meta updating bias correction convergence speed

2019-10-18abs ↗pdf ↗

Globally-Optimal Greedy Experiment Selection for Active Sequential Estimationmath.ST

New methods optimize experiment selection for sequential data, improving model accuracy.

problem Optimizing experiment selection for sequential data in multidimensional cases.

method Adopting greedy experiment selection methods for maximum likelihood estimation.

result Proposed methods produce consistent and asymptotically normal estimators.

experiment selection sequential estimation maximum likelihood stochastic approximation greedy algorithms

2024-02-13abs ↗pdf ↗

On Learning Discrete Graphical Models Using Greedy Methodscs.LG

In this paper, we address the problem of learning the structure of a pairwise graphical model from samples in a high-dimensional setting. Our first main result studies the sparsistency, or consistency in sparsity pattern recovery, properties of a forward-backward greedy algorithm as applied to general statistical model…

2011-07-16abs ↗pdf ↗

Learning Restricted Boltzmann Machines with Arbitrary External Fieldscs.LG

Algorithm learns RBMs with arbitrary external fields, improving on previous constraints.

problem Learning RBMs with arbitrary external fields, improving on previous constraints.

method Greedy algorithm that maximizes covariance between observed nodes sharing latent neighbors.

result Algorithm can learn RBMs with arbitrary external fields, improving on previous constraints.

Restricted Boltzmann Machines Arbitrary External Fields Graphical Models Latent Variables Greedy Algorithm

2019-06-15abs ↗pdf ↗

Stream Clipper: Scalable Submodular Maximization on Streamstat.ML

We propose a streaming submodular maximization algorithm "stream clipper" that performs as well as the offline greedy algorithm on document/video summarization in practice. It adds elements from a stream either to a solution set $S$ or to an extra buffer $B$ based on two adaptive thresholds, and improves $S$ by a final…

2016-06-01abs ↗pdf ↗

Efficient Neighborhood Selection for Gaussian Graphical Modelsstat.ML

This paper addresses the problem of neighborhood selection for Gaussian graphical models. We present two heuristic algorithms: a forward-backward greedy algorithm for general Gaussian graphical models based on mutual information test, and a threshold-based algorithm for walk summable Gaussian graphical models. Both alg…

2015-09-22abs ↗pdf ↗

Conditional Distribution Compression via the Kernel Conditional Mean Embeddingstat.ML

A new method compresses conditional distributions of labelled data.

problem No existing method directly compresses the conditional distribution of labelled data.

method Introduce Average Maximum Conditional Mean Discrepancy (AMCMD), derive a closed form estimator, and extend Kernel Herding (KH) to Average Conditional Kernel Herding (ACKH).

result Directly compressing conditional distributions outperforms joint distribution compression and greedy selection.

distribution compression conditional mean embedding kernel herding greedy algorithm joint distribution

2025-04-14abs ↗pdf ↗

Multinomial Random Forest: Toward Consistency and Privacy-Preservationcs.LG

Proposes MRF for consistency and privacy in RF.

problem Insufficient theoretical understanding of RF's consistency and privacy.

method Introduces MRF with multinomial distributions for feature and value selection.

result Proves MRF's consistency and analyzes its privacy within differential privacy.

random forest consistency privacy multinomial distribution differential privacy

2019-03-10abs ↗pdf ↗

Maximizing acquisition functions for Bayesian optimizationstat.ML

Bayesian optimization uses acquisition functions to find optimal solutions efficiently.

problem Maximizing acquisition functions is difficult due to their complexity and non-convexity.

method Developed gradient-based optimization for Monte Carlo integration of acquisition functions and identified families of acquisition functions that can be maximized using greedy approaches.

result Greedy approaches can be used to maximize acquisition functions, making Bayesian optimization more practical.

Bayesian optimization acquisition functions Monte Carlo integration greedy optimization non-convex functions

2018-05-25abs ↗pdf ↗

Combinatorial Stochastic-Greedy Banditcs.LG

New algorithm for combinatorial bandit problems reduces regret.

problem Optimal selection of sets of arms in bandit problems.

method SGB algorithm with optimized exploration of unselected arms.

result Achieves

(1-1/e)

-regret bound of

\mathcal{O}(n^{\frac{1}{3}} k^{\frac{2}{3}} T^{\frac{2}{3}} \log(T)^{\frac{2}{3}})

bandit problems stochastic-greedy social influence maximization submodular rewards regret bound

2023-12-13abs ↗pdf ↗

Local Anti-Concentration Class: Logarithmic Regret for Greedy Linear Contextual Banditstat.ML

Greedy algorithm achieves sublinear regret for various distributions.

problem Efficient performance of greedy algorithms in linear contextual bandit problems.

method Introduced Local Anti-Concentration (LAC) condition to ensure sublinear regret.

result Greedy algorithm achieves

O(\operatorname{poly} \log T)

cumulative expected regret.

greedy algorithm linear contextual bandit sublinear regret Local Anti-Concentration various distributions

2024-11-19abs ↗pdf ↗

A greedy algorithm for habit formation under multiplicative utilityq-fin.PM

Greedy algorithm optimizes consumption habits with power utility.

problem Optimizing lifetime consumption with habit formation under power utility.

method Developed a greedy algorithm using Monte Carlo simulation.

result Greedy solution is a good approximation to the optimal solution.

habit formation power utility greedy algorithm lifetime consumption Monte Carlo simulation

2023-05-08abs ↗pdf ↗

Beyond Adaptive Submodularity: Approximation Guarantees of Greedy Policy with Adaptive Submodularity Ratiocs.LG

Greedy policy achieves good results for adaptive submodular problems.

problem Sequential decision making with adaptive stochastic optimization.

method Adaptive submodularity ratio to analyze greedy policy performance.

result Greedy policy achieves approximation guarantees for a broader class of problems.

adaptive submodularity greedy policy sequential decision making stochastic optimization approximation guarantees

2019-04-24abs ↗pdf ↗

Greedy AutoAugmentcs.LG

Greedy AutoAugment improves accuracy with less computation.

problem Finding effective data augmentation policies to cover the search space.

method Greedy approach to reduce the number of trials from exponential to linear growth.

result Greedy AutoAugment increases accuracy by 360 times with fewer resources.

data augmentation autoaugment greedy search accuracy computational efficiency

2019-08-02abs ↗pdf ↗

Info-Greedy sequential adaptive compressed sensingcs.IT

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…

2014-07-02abs ↗pdf ↗

TAROT: Targeted Data Selection via Optimal Transportcs.LG

TAROT improves data selection for complex multimodal distributions.

problem Suboptimal data selection in multimodal distributions.

method TAROT uses optimal transport theory to select data, addressing greedy heuristics' limitations.

result TAROT outperforms state-of-the-art methods across various deep learning tasks.

optimal transport data selection multimodal distributions influence estimation greedy heuristics

2024-11-30abs ↗pdf ↗

Fast and explainable clustering based on sortingcs.LG

CLASSIX is a fast and explainable clustering method that sorts data and merges groups.

problem Clustering of data with various shapes and dimensions.

method Greedy aggregation followed by cluster merging with scalar parameters.

result CLASSIX performs competitively with state-of-the-art algorithms and provides intuitive explanations.

clustering greedy algorithm explanation sorting minimal cluster size

2022-02-03abs ↗pdf ↗

New Classes of the Greedy-Applicable Arm Feature Distributions in the Sparse Linear Bandit Problemcs.LG

New distributions allow greedy arm selection in sparse bandit problems.

problem Sparse contextual bandit problem with sparse parameters and feature distributions.

method Introduced new distribution classes and demonstrated that mixtures of these distributions are also greedy-applicable.

result Greedy algorithm applicable to a wider range of arm feature distributions, including those with origin-asymmetric support.

Sparse Bandit Greedy Selection Feature Distributions Origin-Symmetry Mixture Distributions

2023-12-19abs ↗pdf ↗