arXiv research

DRL agents perform poorly at high decision frequencies, but a new algorithm improves performance.

Entrocraft addresses RL performance saturation in LLMs by customizing entropy curves.

Modified BFGS and LBFGS++ libraries boost performance for non-parallelizable functions.

The paper proposes biased advantage estimates for reinforcement learning, improving efficiency and performance.

Advantage amplification helps RL in slow-evolving latent-state environments.

Deep neural networks improve angle of arrival estimation with lower complexity.

Approximate dynamic programming algorithms, such as approximate value iteration, have been successfully applied to many complex reinforcement learning tasks, and a better approximate dynamic programming algorithm is expected to further extend the applicability of reinforcement learning to various tasks. In this paper w…

Quantum walks are at the heart of modern quantum technologies. They allow to deal with quantum transport phenomena and are an advanced tool for constructing novel quantum algorithms. Quantum walks on graphs are fundamentally different from classical random walks analogs, in particular, they walk faster than classical o…

This study improves quantum classifiers by optimizing data preprocessing.

This paper improves SVD for recommender systems using block-based matrix factorization.

Study compares adaptive vs fixed query learning methods.

Improved SAC with AWMP for better control tasks.

The potential positive impact of autonomous driving and driver assistance technolo- gies have been a major impetus over the last decade. On the flip side, it has been a challenging problem to analyze the performance of human drivers or autonomous driving agents quantitatively. In this work, we propose a generic method …

Convolutional networks outperform fully-connected ones in certain tasks.

Paper tackles unfair advantages in DARTS, presenting Fair DARTS to improve neural architecture search.

Quantum networks offer exponential communication savings for large machine learning models.

Two new criteria help understand the advantage of deep neural networks.

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

Conditional meta-learning improves meta-learning performance in diverse task environments.

Small LLMs outperform large ones on simple tasks without extra labelling costs.

New model learning objective improves continuous control tasks.

MB-DQN uses different backup lengths for improved reinforcement learning.

Quantum Boltzmann Machines trained on quantum annealers produce noisy synthetic data.

Real-world tasks are often highly structured. Hierarchical reinforcement learning (HRL) has attracted research interest as an approach for leveraging the hierarchical structure of a given task in reinforcement learning (RL). However, identifying the hierarchical policy structure that enhances the performance of RL is n…

Bayesian estimators for causal inference using hierarchical Gaussian Processes.

Paper proposes Terminal Prediction to improve deep RL performance.

Paper introduces DTAE to optimize RL algorithms, balancing exploration and exploitation.

Proposes GPHMEs using Gaussian processes for hierarchical expert models.

The study examines how experimental design choices affect machine learning model performance.

In traditional reinforcement learning, an agent maximizes the reward collected during its interaction with the environment by approximating the optimal policy through the estimation of value functions. Typically, given a state s and action a, the corresponding value is the expected discounted sum of rewards. The optima…

Bayesian co-clustering model for mixed data tables.

Bayesian MAML outperforms MAML in meta learning tasks with theoretical guarantees.

We propose a simple method that combines neural networks and Gaussian processes. The proposed method can estimate the uncertainty of outputs and flexibly adjust target functions where training data exist, which are advantages of Gaussian processes. The proposed method can also achieve high generalization performance fo…

In the multiple linear regression setting, we propose a general framework, termed weighted orthogonal components regression (WOCR), which encompasses many known methods as special cases, including ridge regression and principal components regression. WOCR makes use of the monotonicity inherent in orthogonal components …

This review analyzes RL in finance, highlighting its advantages and challenges.

Memory split advantage: thinner networks outperform a single wide network.

DARTS- improves robustness by factoring out skip connections' advantage.

Quantum algorithms improve VaR and CVaR estimation for financial derivatives.

Policy optimization on high-dimensional continuous control tasks exhibits its difficulty caused by the large variance of the policy gradient estimators. We present the action subspace dependent gradient (ASDG) estimator which incorporates the Rao-Blackwell theorem (RB) and Control Variates (CV) into a unified framework…

Quantum machine learning offers advantages for broader learning tasks.

Machine learning approaches to multi-label document classification have to date largely relied on discriminative modeling techniques such as support vector machines. A drawback of these approaches is that performance rapidly drops off as the total number of labels and the number of labels per document increase. This pr…

This paper improves Q-learning bounds using reference-advantage decomposition.

New approach optimizes policies in adversarial MDPs using adversarial learning.

Signature kernel handles sequential data with theoretical and practical advantages.

In this article, we advance divide-and-conquer strategies for solving the community detection problem in networks. We propose two algorithms which perform clustering on a number of small subgraphs and finally patches the results into a single clustering. The main advantage of these algorithms is that they bring down si…

Model-free reinforcement learning agents outperform traditional portfolio management models in asset allocation.

Improved A2C method with lower variance.

Many methods have been proposed for community detection in networks, but most of them do not take into account additional information on the nodes that is often available in practice. In this paper, we propose a new joint community detection criterion that uses both the network edge information and the node features to…