arXiv research

FLAMBE tackles RL in low rank MDPs by learning features.

New method normalizes matrix features for robust low-rank approximation.

Develops efficient method for updating models with small data changes.

Proposes a method to learn from multiple views with low-rank embeddings.

This work explores efficient reinforcement learning with density features in low-rank MDPs.

This paper extends neural collapse to regression problems, revealing key features and structures.

We investigate the effect of the dimensionality of the representations learned in Deep Neural Networks (DNNs) on their robustness to input perturbations, both adversarial and random. To achieve low dimensionality of learned representations, we propose an easy-to-use, end-to-end trainable, low-rank regularizer (LR) that…

Feature selection methods are widely used in order to solve the 'curse of dimensionality' problem. Many proposed feature selection frameworks, treat all data points equally; neglecting their different representation power and importance. In this paper, we propose an unsupervised hypergraph feature selection method via …

New training scheme reduces adversarial examples by increasing decision boundary margin.

RFM reduces feature space for linear models, improving sparse recovery.

New method selects features via tensor decomposition and submodular optimization.

TSRGA scales multivariate linear regression for feature-distributed data.

The study assesses low-rank approximations in Gaussian Process regression.

Algorithm reduces high-dimensional SLB regret by exploiting hidden low-rank structure.

The study assesses low-rank approximations in Gaussian Process regression.

Exponentially fast SMF algorithm for multi-class classification.

EML model tackles evolving features in online metric learning.

Paper introduces G-LowTESTR for efficient tensor bandits.

New algorithm for weighted low rank approximation with provable guarantees.

Paper tackles dynamic assortment with dual contexts, improving revenue in e-commerce.

Deep MF extracts hierarchical features from large data sets.

New model reduces matrix factorization bias, yielding truly low-rank solutions.

Principal components analysis (PCA) is a well-known technique for approximating a tabular data set by a low rank matrix. Here, we extend the idea of PCA to handle arbitrary data sets consisting of numerical, Boolean, categorical, ordinal, and other data types. This framework encompasses many well known techniques in da…

Meta learns low-rank covariance factors for better uncertainty estimation.

Develops PRPCA for smooth image recovery combining low-rank and smoothness.

Improved LoRA+ adapts large models more efficiently.

This paper presents privileged multi-label learning (PrML) to explore and exploit the relationship between labels in multi-label learning problems. We suggest that for each individual label, it cannot only be implicitly connected with other labels via the low-rank constraint over label predictors, but also its performa…

We consider the problem of learning a low-rank matrix, constrained to lie in a linear subspace, and introduce a novel factorization for modeling such matrices. A salient feature of the proposed factorization scheme is it decouples the low-rank and the structural constraints onto separate factors. We formulate the optim…

In the paper, we consider the problem of link prediction in time-evolving graphs. We assume that certain graph features, such as the node degree, follow a vector autoregressive (VAR) model and we propose to use this information to improve the accuracy of prediction. Our strategy involves a joint optimization procedure …

Quantum algorithm speeds up learning from big data exponentially.

AIR-Net adapts low-rank regularization dynamically for better image completion.

This work examines how low-rank weights improve adversarial robustness in neural networks.

As opposed to manual feature engineering which is tedious and difficult to scale, network representation learning has attracted a surge of research interests as it automates the process of feature learning on graphs. The learned low-dimensional node vector representation is generalizable and eases the knowledge discove…

New method accelerates CNNs for mobile devices by approximating tensors and quantizing weights.

We consider a challenging multi-label classification problem where both feature matrix $\X$ and label matrix $\Y$ have missing entries. An existing method concatenated $\X$ and $\Y$ as $[\X; \Y]$ and applied a matrix completion (MC) method to fill the missing entries, under the assumption that $[\X; \Y]$ is of low-rank…

We consider the problem of learning a high-dimensional but low-rank matrix from a large-scale dataset distributed over several machines, where low-rankness is enforced by a convex trace norm constraint. We propose DFW-Trace, a distributed Frank-Wolfe algorithm which leverages the low-rank structure of its updates to ac…

New method uses tensor decompositions to overcome the curse of dimensionality for large-scale learning.

New RL algorithm maximizes CVaR in low-rank MDPs with provable efficiency.

The effectiveness of supervised learning techniques has made them ubiquitous in research and practice. In high-dimensional settings, supervised learning commonly relies on dimensionality reduction to improve performance and identify the most important factors in predicting outcomes. However, the economic importance of …

Proposes a low-rank deep CNN for multi-task learning.

We propose a sparse and low-rank tensor regression model to relate a univariate outcome to a feature tensor, in which each unit-rank tensor from the CP decomposition of the coefficient tensor is assumed to be sparse. This structure is both parsimonious and highly interpretable, as it implies that the outcome is related…

Deep ReLU networks escape from the origin via saddle points with a low-rank bias.

This paper offers a characterization of fundamental limits on the classification and reconstruction of high-dimensional signals from low-dimensional features, in the presence of side information. We consider a scenario where a decoder has access both to linear features of the signal of interest and to linear features o…

We consider dynamic pricing with many products under an evolving but low-dimensional demand model. Assuming the temporal variation in cross-elasticities exhibits low-rank structure based on fixed (latent) features of the products, we show that the revenue maximization problem reduces to an online bandit convex optimiza…

New findings show DNC is not optimal for deep models, revealing a low-rank bias.

Data often comes in the form of an array or matrix. Matrix factorization techniques attempt to recover missing or corrupted entries by assuming that the matrix can be written as the product of two low-rank matrices. In other words, matrix factorization approximates the entries of the matrix by a simple, fixed function-…

LoRAs enable efficient adaptation of large models; this paper explores processing LoRA weights with machine learning.

New algorithm tackles bilinear bandit problem with low-rank structure.