arXiv research

This work improves structured prediction by learning the balance between signal and random noise.

Free Random Projection enhances reinforcement learning by naturally incorporating hierarchical structure.

Improved random forest models enhance machine learning predictions.

RandNLA uses randomness for matrix problems in machine learning.

Algorithm learns CNF formulas from random solutions under specific conditions.

Analyzes biased random walks and corrupted intervals in adversarial settings.

Efficient privacy-preserving machine learning framework using random transformations.

This study examines how randomness affects machine learning model performance.

Online random forests improve Q-learning performance in specific gym environments.

Random learning rate improves neural network training without extra cost.

Improved random forest proximities capture data geometry.

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…

UniNet efficiently learns network representations from large graphs.

Learn low-degree functions with few random queries.

A new approach models exploration in continuous-time RL using random measures.

Random feature maps improve forecasting with cheaper computation.

New method stabilizes machine learning predictions across random seeds.

Domain randomization (DR) is a successful technique for learning robust policies for robot systems, when the dynamics of the target robot system are unknown. The success of policies trained with domain randomization however, is highly dependent on the correct selection of the randomization distribution. The majority of…

Sparse random networks reduce communication in federated learning.

The random subspace method, known as the pillar of random forests, is good at making precise and robust predictions. However, there is not a straightforward way yet to combine it with deep learning. In this paper, we therefore propose Neural Random Subspace (NRS), a novel deep learning based random subspace method. In …

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

The paper outlines future work in random sets theory.

Introduces epistemic deep learning for better uncertainty estimation in neural networks.

Sparse random features improve accuracy in data-scarce settings.

Random feature models approximate functions in Banach spaces efficiently.

RandQL is a new model-free algorithm for MDPs with a novel learning rate randomization approach.

This study improves scalability of randomized smoothing for certifying classifier robustness.

The randomized-feature approach has been successfully employed in large-scale kernel approximation and supervised learning. The distribution from which the random features are drawn impacts the number of features required to efficiently perform a learning task. Recently, it has been shown that employing data-dependent …

New algorithm learns random neural networks efficiently.

We propose accelerated randomized coordinate descent algorithms for stochastic optimization and online learning. Our algorithms have significantly less per-iteration complexity than the known accelerated gradient algorithms. The proposed algorithms for online learning have better regret performance than the known rando…

Random neural nets learn Black-Scholes PDEs without dimensionality issues.

Paper introduces a method for operator learning using random features.

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…

Study compares memorization of SimCLR to supervised and random labels training.

We propose random hinge forests, a simple, efficient, and novel variant of decision forests. Importantly, random hinge forests can be readily incorporated as a general component within arbitrary computation graphs that are optimized end-to-end with stochastic gradient descent or variants thereof. We derive random hinge…

Overview of high-dimensional dynamical systems and their applications to machine learning.

Extends RL to random stopping times, improving optimization.

Proposes a link between randomness and compression in deep learning.

We propose reinforcement learning on simple networks consisting of random connections of spiking neurons (both recurrent and feed-forward) that can learn complex tasks with very little trainable parameters. Such sparse and randomly interconnected recurrent spiking networks exhibit highly non-linear dynamics that transf…

Gradient span algorithms show consistent progress in high dimensions.

Enhanced ELM reduces randomness in neural network training.

Study improves prediction accuracy and uncertainty for mobile sensor data using randomized neural networks.

Randomness is crucial for stability in learning and statistics, especially for differential privacy.

Machine learning improves kidney transplant outcomes prediction.

This study compares machine learning methods for high-cardinality categorical variables.

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

DiAL uses Bayesian Dirichlet random fields for active learning with sparse labels.

Randomized predictions ensure fair and accurate individual calibration in machine learning.