arXiv research

A simple sketch improves online eigenvector and SDP problems.

BiQGEMM efficiently multiplies quantized DNN weights using lookup tables.

Dynamic sparseness reduces neural network computation by selectively omitting parts of computations.

MSD removes dequantization bottleneck in LLM inference by approximating high-precision activations.

This paper presents a novel multitask multiple kernel learning framework that efficiently learns the kernel weights leveraging the relationship across multiple tasks. The idea is to automatically infer this task relationship in the \textit{RKHS} space corresponding to the given base kernels. The problem is formulated a…

New algorithm speeds up group equivariant neural networks computations.

AWNN improves matrix completion by adaptively weighting nearest neighbors.

Improved MMWU algorithm achieves instance-optimal regret bound for matrix LEA.

clusterBMA combines clustering results from multiple models using Bayesian model averaging.

Paper introduces SMM for forecasting multiple time series with missing values.

New algorithm for online optimization over symmetric cones, unifying previous methods.

New NMF algorithm uses Toeplitz matrix for facial recognition.

New algorithm solves empirical risk minimization problems in current matrix multiplication time.

Proposes a novel multi-view clustering method by aligning partitions.

Proposes WM-NMF for better multi-view clustering.

Improved hypothesis testing and change-point detection using diffusion-based methods.

Graph convolutional network (GCN) is generalization of convolutional neural network (CNN) to work with arbitrarily structured graphs. A binary adjacency matrix is commonly used in training a GCN. Recently, the attention mechanism allows the network to learn a dynamic and adaptive aggregation of the neighborhood. We pro…

New algorithm provably converges to second-order stationary points in NMF.

A new model estimates mixed memberships for categorical data with weighted responses.

Interpretable machine-learning models can be unstable under multicollinearity, leading to oscillatory weights that do not reflect meaningful contributions.

RMCSE improves voltage estimation in low-observability distribution systems.

Paper speeds up matrix multiplication on Intel PIII using SIMD.

In this paper, we provide a novel construction of the linear-sized spectral sparsifiers of Batson, Spielman and Srivastava [BSS14]. While previous constructions required $Ω(n^4)$ running time [BSS14, Zou12], our sparsification routine can be implemented in almost-quadratic running time $O(n^{2+\varepsilon})$. The funda…

New method optimizes matrix denoising for weighted loss functions and heterogeneous signals.

Connections between nodes of fully connected neural networks are usually represented by weight matrices. In this article, functional transfer matrices are introduced as alternatives to the weight matrices: Instead of using real weights, a functional transfer matrix uses real functions with trainable parameters to repre…

Iteratively reweighted least squares (IRLS) is a widely-used method in machine learning to estimate the parameters in the generalised linear models. In particular, IRLS for L1 minimisation under the linear model provides a closed-form solution in each step, which is a simple multiplication between the inverse of the we…

Given a real matrix A with n columns, the problem is to approximate the Gram product AA^T by c << n weighted outer products of columns of A. Necessary and sufficient conditions for the exact computation of AA^T (in exact arithmetic) from c >= rank(A) columns depend on the right singular vector matrix of A. For a Monte-…

Paper proposes DR-NMF for robust NMF with unknown noise model.

Unweighted matrix factorization can match or outperform weighted methods in recommender systems.

This paper explores how random sampling and coding can speed up approximate matrix multiplication.

Paper develops a new weighted low-rank matrix approximation technique.

The paper introduces a new class of multivariate mixtures for actuarial applications.

Method selects number of communities in weighted networks.

Paper reformulates UOT as non-negative penalized linear regression for efficient algorithms.

The online problem of computing the top eigenvector is fundamental to machine learning. In both adversarial and stochastic settings, previous results (such as matrix multiplicative weight update, follow the regularized leader, follow the compressed leader, block power method) either achieve optimal regret but run slow,…

Study evaluates thresholds for removing noise from DNN weights using random matrix theory.

Efficient and accurate low-rank approximations of multiple data sources are essential in the era of big data. The scaling of kernel-based learning algorithms to large datasets is limited by the O(n^2) computation and storage complexity of the full kernel matrix, which is required by most of the recent kernel learning a…

Develops theory of weightings for Lie groupoids and algebroids.

Weight normalization speeds up matrix sensing problems.

Recently theoretical guarantees have been obtained for matrix completion in the non-uniform sampling regime. In particular, if the sampling distribution aligns with the underlying matrix's leverage scores, then with high probability nuclear norm minimization will exactly recover the low rank matrix. In this article, we…

We consider the following multi-component sparse PCA problem: given a set of data points, we seek to extract a small number of sparse components with disjoint supports that jointly capture the maximum possible variance. These components can be computed one by one, repeatedly solving the single-component problem and def…

Proposes improved classification via transfer learning with regularized linear discriminant analysis.

Localized sketching improves matrix multiplication and ridge regression complexity.

This paper finds a new way to compress CNN weights, improving on pruning and quantization.

We introduce a covariance matrix estimator that both takes into account the heteroskedasticity of financial returns (by using an exponentially weighted moving average) and reduces the effective dimensionality of the estimation (and hence measurement noise) via techniques borrowed from random matrix theory. We calculate…

A new algorithm reduces communication in distributed SVD by $p$ factors.

New PAC-Bayes bound controls multiple error types simultaneously.

New algorithm for weighted low rank approximation with provable guarantees.