arXiv research

Quantum machine learning offers advantages for broader learning tasks.

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

DG improves policy gradients by weighting actions with a sigmoid of advantage and surprisal.

UCB-Advantage learns MDPs with $O(\sqrt{H^2SAT})$ regret.

Quantum effects are known to provide an advantage in particle transfer across networks. In order to achieve this advantage, requirements on both a graph type and a quantum system coherence must be found. Here we show that the process of finding these requirements can be automated by learning from simulated examples. Th…

New method learns time-varying home field advantage in football.

Study compares adaptive vs fixed query learning methods.

Study on when RLVR can learn compositional problems.

Quantum advantage in derivative pricing requires 8k qubits and 54M T-depth.

Gradient descent benefits from tangent kernel advantages under specific conditions.

We develop Riemannian Stein Variational Gradient Descent (RSVGD), a Bayesian inference method that generalizes Stein Variational Gradient Descent (SVGD) to Riemann manifold. The benefits are two-folds: (i) for inference tasks in Euclidean spaces, RSVGD has the advantage over SVGD of utilizing information geometry, and …

This paper discusses a counterpart of conformal prediction for e-values, conformal e-prediction. Conformal e-prediction is conceptually simpler and had been developed in the 1990s as a precursor of conformal prediction. When conformal prediction emerged as result of replacing e-values by p-values, it seemed to have imp…

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

Quantum algorithms accelerate financial risk computation.

Latent-state environments with long horizons, such as those faced by recommender systems, pose significant challenges for reinforcement learning (RL). In this work, we identify and analyze several key hurdles for RL in such environments, including belief state error and small action advantage. We develop a general prin…

The paper tackles scalarization issues in A2C RL algorithms, proposing methods to avoid gradient overlap and noise.

New proof shows local wealth condensation in economic models with biases.

DG separates successes and failures by gating updates with advantage and surprisal.

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

This study improves quantum classifiers by optimizing data preprocessing.

Quantum circuits reveal pathways to dequantization in machine learning models.

VQAs use classical optimization to train quantum circuits, promising quantum advantage.

Convolutional networks outperform fully-connected ones in certain tasks.

Quantum algorithms improve VaR and CVaR estimation for financial derivatives.

Quantum computing offers energy savings over classical computing.

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…

Sparse activations in neural networks are hard to exploit but lead to advantages in learning.

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…

Bayesian estimators for causal inference using hierarchical Gaussian Processes.

Paper proposes FedQ-Advantage for federated Q-learning with near-optimal regret and low communication cost.

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

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

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

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

Hybrid quantum-classical RL model solves standard benchmark tasks and proves quantum advantage.

With the abundance of data in recent years, interesting challenges are posed in the area of recommender systems. Producing high quality recommendations with scalability and performance is the need of the hour. Singular Value Decomposition(SVD) based recommendation algorithms have been leveraged to produce better result…

Distributed securities exchanges may become de facto fragmented if they span geographical regions with asymmetric computer infrastructure. First, we build an economic model of a decentralized exchange with two miner clusters, standing in for compact areas of economic activity (e.g., cities). "Local" miners in the area …

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…

In the past decade, the field of quantum machine learning has drawn significant attention due to the prospect of bringing genuine computational advantages to now widespread algorithmic methods. However, not all domains of machine learning have benefited equally from quantum enhancements. Notably, deep learning and rein…

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

One question central to Reinforcement Learning is how to learn a feature representation that supports algorithm scaling and re-use of learned information from different tasks. Successor Features approach this problem by learning a feature representation that satisfies a temporal constraint. We present an implementation…

The estimation of advantage is crucial for a number of reinforcement learning algorithms, as it directly influences the choices of future paths. In this work, we propose a family of estimates based on the order statistics over the path ensemble, which allows one to flexibly drive the learning process, towards or agains…

Enhances time-series modeling by dropping patches, improving efficiency and adaptability.

Normalizing flows are deep generative models that allow efficient likelihood calculation and sampling. The core requirement for this advantage is that they are constructed using functions that can be efficiently inverted and for which the determinant of the function's Jacobian can be efficiently computed. Researchers h…

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

Investors suffer welfare loss despite having better information.

Quantum correlations enhance generative models, providing a new resource for machine learning.

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