arXiv research

A new ZSL algorithm uses shared sparse representations for unseen classes.

New approach improves cross-domain recommendation for sparse target domains.

Unsupervised methods have proven effective for discriminative tasks in a single-modality scenario. In this paper, we present a multimodal framework for learning sparse representations that can capture semantic correlation between modalities. The framework can model relationships at a higher level by forcing the shared …

Dockless bike sharing systems need effective bike flow prediction models.

Improved AutoDML estimator for causal inference using outcome-adapted shared covariate representation.

SANs use sparse activation functions to compress data representations.

Boosts share routing for multi-task learning with flexible sparse connections.

SANs use sparse activation functions to minimize model complexity.

CMF is a technique for simultaneously learning low-rank representations based on a collection of matrices with shared entities. A typical example is the joint modeling of user-item, item-property, and user-feature matrices in a recommender system. The key idea in CMF is that the embeddings are shared across the matrice…

Deep learning boosts building energy load forecasting.

New method identifies latent variables with sparse perturbations.

We consider high-dimensional distribution estimation through autoregressive networks. By combining the concepts of sparsity, mixtures and parameter sharing we obtain a simple model which is fast to train and which achieves state-of-the-art or better results on several standard benchmark datasets. Specifically, we use a…

Content based image retrieval, a technique which uses visual contents of image to search images from large scale image databases according to users' interests. This paper provides a comprehensive survey on recent technology used in the area of content based face image retrieval. Nowadays digital devices and photo shari…

MT-HAL learns features and task associations for multiple tasks with a shared sparse structure.

Sparse portfolio strategy from mutual funds' favorite stocks in China A share market.

New algorithm reduces communication in distributed learning by sharing compressed beliefs.

Improves shared encoder representations for better multi-task learning performance.

BEAN models neuronal correlations to create interpretable representations.

Sparse linear regression -- finding an unknown vector from linear measurements -- is now known to be possible with fewer samples than variables, via methods like the LASSO. We consider the multiple sparse linear regression problem, where several related vectors -- with partially shared support sets -- have to be recove…

UCB-TQL learns from multiple tasks with shared dynamics and adapts to task-specific variations.

New method clusters multi-view data by squeezing hybrid knowledge.

The paper proposes a model to learn disentangled representations using mutual information.

HCL learns shared and modality-specific latent representations for multimodal data.

This research shows how to learn shared representations from unpaired data.

First-order ANIL learns shared representations even with overparametrization.

A variety of representation learning approaches have been investigated for reinforcement learning; much less attention, however, has been given to investigating the utility of sparse coding. Outside of reinforcement learning, sparse coding representations have been widely used, with non-convex objectives that result in…

Many signal processing and machine learning methods share essentially the same linear-in-the-parameter model, with as many parameters as available samples as in kernel-based machines. Sparse approximation is essential in many disciplines, with new challenges emerging in online learning with kernels. To this end, severa…

A novel approach tackles sparse linear bandits with reduced communication costs and minimal cumulative regret.

New algorithm extracts shared latent space for cortico-muscular interactions.

Unpaired multi-domain causal representation learning is possible with sufficient conditions.

We investigate sparse representations for control in reinforcement learning. While these representations are widely used in computer vision, their prevalence in reinforcement learning is limited to sparse coding where extracting representations for new data can be computationally intensive. Here, we begin by demonstrat…

Paper shows how sparse inversion speeds up log determinant derivatives.

A new method for multiclass calibration using vector quantization.

New algorithms minimize regret in multi-task and lifelong linear bandits with shared representation.

ALF reduces network parameters and operations by 70% and 61%, respectively, on embedded hardware.

GmGM models multi-axis data for faster analysis.

We study the problem of distributed multi-task learning with shared representation, where each machine aims to learn a separate, but related, task in an unknown shared low-dimensional subspaces, i.e. when the predictor matrix has low rank. We consider a setting where each task is handled by a different machine, with sa…

User response prediction makes a crucial contribution to the rapid development of online advertising system and recommendation system. The importance of learning feature interactions has been emphasized by many works. Many deep models are proposed to automatically learn high-order feature interactions. Since most featu…

New bounds on learning shared representations improve model performance and efficiency.

Theoretical analysis of CNNs' inductive biases and their efficiency in approximating functions.

This paper investigates learning sparse representations and action-value functions simultaneously in deep reinforcement learning.

DBRec discovers latent groups to improve recommendation.

Sparse coding is a common approach to learning local features for object recognition. Recently, there has been an increasing interest in learning features from spatio-temporal, binocular, or other multi-observation data, where the goal is to encode the relationship between images rather than the content of a single ima…

Most artificial networks today rely on dense representations, whereas biological networks rely on sparse representations. In this paper we show how sparse representations can be more robust to noise and interference, as long as the underlying dimensionality is sufficiently high. A key intuition that we develop is that …

Improves NILM with multi-label SRC, outperforming state-of-the-art.

Data is said to follow the transform (or analysis) sparsity model if it becomes sparse when acted on by a linear operator called a sparsifying transform. Several algorithms have been designed to learn such a transform directly from data, and data-adaptive sparsifying transforms have demonstrated excellent performance i…

Sparse representations using data dictionaries provide an efficient model particularly for signals that do not enjoy alternate analytic sparsifying transformations. However, solving inverse problems with sparsifying dictionaries can be computationally expensive, especially when the dictionary under consideration has a …

We present a transductive deep learning-based formulation for the sparse representation-based classification (SRC) method. The proposed network consists of a convolutional autoencoder along with a fully-connected layer. The role of the autoencoder network is to learn robust deep features for classification. On the othe…