arXiv research

Optimal iterative thresholding algorithms improve upon hard and soft thresholding.

The article examines different thresholding methods for improving PAM algorithm in cancer classification.

New algorithm for reinforcement learning in uncertain environments with unknown thresholds.

LSA minimizes aggregate regret in thresholding bandit with optimal performance.

A new algorithm infers causal networks from data using topological thresholds.

New algorithm identifies good arms with fewer samples when thresholds are close.

Noise makes learning linear thresholds hard, but algorithms can still learn near-optimal thresholds.

Paper discusses new stochastic algorithms for sparse signal recovery.

Adaptive algorithm for outlier detection by balancing arm exploration and threshold estimation.

Study derives algorithmic detectability threshold for stochastic block model with EM and BP.

New algorithm detects communities even with corrupted data, reaching Kesten-Stigum threshold.

Iterative shrinkage/thresholding algorithm (ISTA) is a well-studied method for finding sparse solutions to ill-posed inverse problems. In this letter, we present a data-driven scheme for learning optimal thresholding functions for ISTA. The proposed scheme is obtained by relating iterations of ISTA to layers of a simpl…

A RL algorithm learns optimal multi-threshold policies for MDPs.

Sparse reconstruction approaches using the re-weighted l1-penalty have been shown, both empirically and theoretically, to provide a significant improvement in recovering sparse signals in comparison to the l1-relaxation. However, numerical optimization of such penalties involves solving problems with l1-norms in the ob…

Paper develops algorithms to maximize AUC in imbalanced classification.

LinearAPT optimizes decision-making under resource constraints for a linear threshold problem.

Automatically tunes distance threshold in metric learning.

Optimal algorithm for identifying best arm in stochastic linear bandits with fixed confidence.

This study optimizes multi-modal learning thresholds and algorithms in high dimensions.

Hard thresholding remains efficient for DNN pruning, but smart pruning offers faster accuracy recovery.

New RGraSP framework for efficient non-convex optimization.

This paper considers the problem of estimating multiple related Gaussian graphical models from a $p$-dimensional dataset consisting of different classes. Our work is based upon the formulation of this problem as group graphical lasso. This paper proposes a novel hybrid covariance thresholding algorithm that can effecti…

Iterative thresholding algorithms are well-suited for high-dimensional problems in sparse recovery and compressive sensing. The performance of this class of algorithms depends heavily on the tuning of certain threshold parameters. In particular, both the final reconstruction error and the convergence rate of the algori…

Paper finds a fast method for a matrix norm proximal operator.

Study uses SGD to learn optimal thresholds for buying and selling stocks.

Paper analyzes adaptive ISTA with MAD for LASSO problem.

The stochastic block model is one of the oldest and most ubiquitous models for studying clustering and community detection. In an exciting sequence of developments, motivated by deep but non-rigorous ideas from statistical physics, Decelle et al. conjectured a sharp threshold for when community detection is possible in…

New RL algorithm learns optimal policies for MDPs using known structure.

Solves community detection in sparse hypergraphs above a threshold.

Thresholded Lasso bandit minimizes regret in sparse linear bandits.

Study analyzes sample complexity of thresholding bandit for dose-ranging, with and without monotonicity assumption.

Optimal method detects jumps in jump-diffusion processes.

New algorithm achieves strong consistency in binary non-uniform hypergraph classification.

New insights into binary perceptron reveal phase transitions and algorithmic thresholds.

This paper considers the multi-armed thresholding bandit problem -- identifying all arms whose expected rewards are above a predefined threshold via as few pulls (or rounds) as possible -- proposed by Locatelli et al. [2016] recently. Although the proposed algorithm in Locatelli et al. [2016] achieves the optimal round…

MTSSL optimizes threshold τ for better semi-supervised learning performance.

New algorithm detects communities near KS threshold with optimal rate, even in noisy conditions.

New algorithm resists contamination in high-dimensional regression with optimal performance.

Ridge regression is revisited with debiasing and thresholding, offering advantages over Lasso.

Recently, a novel family of biologically plausible online algorithms for reducing the dimensionality of streaming data has been derived from the similarity matching principle. In these algorithms, the number of output dimensions can be determined adaptively by thresholding the singular values of the input data matrix. …

A new algorithm improves sample complexity for thresholding in Monte Carlo Tree Search.

Optimal rates for learning hidden tree structures are determined.

A new SSL method uses instance-dependent thresholds to improve accuracy.

Study lenient regret and good-action identification in Gaussian process bandits.

Multi-task feature learning aims to identity the shared features among tasks to improve generalization. It has been shown that by minimizing non-convex learning models, a better solution than the convex alternatives can be obtained. Therefore, a non-convex model based on the capped-$\ell_{1},\ell_{1}$ regularization wa…

New method trains neural networks with threshold activation functions efficiently.

Private learning of thresholds requires many examples.

GrAPL identifies arms above a threshold using graph similarity.