arXiv research

Paper proposes diagnostics for error and variance estimation in randomized matrix computations.

LightOn OPUs accelerate randomized numerical linear algebra, reducing computational costs.

Study finds no significant difference in neural network weights with quantum random numbers.

New MBQC algorithm uses randomness for generative modeling.

We discuss the relative merits of optimistic and randomized approaches to exploration in reinforcement learning. Optimistic approaches presented in the literature apply an optimistic boost to the value estimate at each state-action pair and select actions that are greedy with respect to the resulting optimistic value f…

Proposes new random models for fuzzy clustering similarity measures.

Matrix multiplication is a fundamental building block for large scale computations arising in various applications, including machine learning. There has been significant recent interest in using coding to speed up distributed matrix multiplication, that are robust to stragglers (i.e., machines that may perform slower …

New methods improve Reservoir Computing for chaotic time series prediction.

New methods improve prediction performance and reduce computation time in boosting and random forest models.

Paper studies binary random projections with controllable sparsity patterns for computational and accuracy advantages.

Random exploration optimizes Bayesian optimization with optimal error rates and computational efficiency.

A faster graph kernel using optical random features.

A new method for efficient nonlinear process monitoring using random Bernoulli features.

New method speeds up solving orthogonality constrained problems.

MindFlayer SGD improves parallel SGD for heterogeneous, random compute times.

We investigate the computational complexity of several basic linear algebra primitives, including largest eigenvector computation and linear regression, in the computational model that allows access to the data via a matrix-vector product oracle. We show that for polynomial accuracy, $Θ(d)$ calls to the oracle are nece…

We describe a model of random links based on random 4-valent maps, which can be sampled due to the work of Schaeffer. We will look at the relationship between the combinatorial information in the diagram and the hyperbolic volume. Specifically, we show that for random alternating diagrams, the expected hyperbolic volum…

Linear time algorithm for random walk kernels on sparse graphs.

We study the generalization properties of ridge regression with random features in the statistical learning framework. We show for the first time that $O(1/\sqrt{n})$ learning bounds can be achieved with only $O(\sqrt{n}\log n)$ random features rather than $O({n})$ as suggested by previous results. Further, we prove fa…

We provide a new extension of Breiman's Theorem on computing tail probabilities of a product of random variables to a multivariate setting. In particular, we give a complete characterization of regular variation on cones in $[0,\infty)^d$ under random linear transformations. This allows us to compute probabilities of a…

Quantum machine learning tackles large datasets with randomized measurements.

NodeSig efficiently computes binary node embeddings for scalable graph analysis.

New method reduces variance in random coordinate descent for Langevin Monte Carlo.

New explanation of reservoir computing using random projections.

We adapt the idea of random projections applied to the output space, so as to enhance tree-based ensemble methods in the context of multi-label classification. We show how learning time complexity can be reduced without affecting computational complexity and accuracy of predictions. We also show that random output spac…

Efficient privacy-preserving machine learning framework using random transformations.

Gradient boosting with randomized trees reduces discontinuities and complexity.

Independent component analysis (ICA) is a method for recovering statistically independent signals from observations of unknown linear combinations of the sources. Some of the most accurate ICA decomposition methods require searching for the inverse transformation which minimizes different approximations of the Mutual I…

TRF uses ternary random features to improve ML performance without extra computation.

Study on detecting and recovering hidden dense cycles in random graphs.

Efficient algorithm approximates discrete random variables with minimal Kolmogorov distance.

RFRBoost uses random features to boost deep residual neural networks, improving performance and computational efficiency.

Random feature method approximates operators with theoretical guarantees and reduced computation.

Logistic regression for brain imaging without p-values.

New DKPP family controls positive and negative dependence in random subsets.

Randomized gradient-based ensemble improves prediction accuracy.

This paper improves computational efficiency in kernel ridge regression under covariate shift.

Computes expected number of real intersection points of essential variety with random linear spaces.

The aim of this short note is to draw attention to a method by which the partition function and marginal probabilities for a certain class of random fields on complete graphs can be computed in polynomial time. This class includes Ising models with homogeneous pairwise potentials but arbitrary (inhomogeneous) unary pot…

Study on using random subspaces for ERM with various loss functions.

Study shows a tradeoff between sample complexity and computational efficiency for learning halfspaces with random noise.

WildWood improves Random Forest predictions using bootstrap out-of-bag samples.

Improved statistical computation through efficient matrix sampling.

Random forest training yields confidence intervals for generalization error.

In this paper we study a model of random knots obtained by fixing a space curve in $n$-dimensional Euclidean space with $n>3$, and orthogonally projecting the space curve on to random $3$ dimensional subspaces. By varying the space curve we obtain different models of random parametrized knots, and we will study how the…

This paper presents a sequential randomized lowrank matrix factorization approach for incrementally predicting values of an unknown function at test points using the Gaussian Processes framework. It is well-known that in the Gaussian processes framework, the computational bottlenecks are the inversion of the (regulariz…

Paper proposes a new financial fraud detection system using improved RF and GBM.

RQMC improves kernel-based learning by reducing deterministic error and offering computational advantages.