arXiv research

Quantum machine learning offers advantages for broader learning tasks.

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 …

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

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

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

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…

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

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

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…

Improved SAC with AWMP for better control tasks.

Woodbury transformations improve deep generative models with efficient invertibility and determinant calculation.

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

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

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

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…

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

Study compares adaptive vs fixed query learning methods.

Deep neural networks outperform other methods in estimating non-smooth functions with singularities.

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

New distributions on manifolds for better sampling.

Study on when RLVR can learn compositional problems.

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

Probabilistic inference in graphical models is the task of computing marginal and conditional densities of interest from a factorized representation of a joint probability distribution. Inference algorithms such as variable elimination and belief propagation take advantage of constraints embedded in this factorization …

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…

Gradient descent benefits from tangent kernel advantages under specific conditions.

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

We study gradient bounds and other functional inequalities for the diffusion semigroup generated by Kolmogorov type operators. The focus is on two different methods: coupling techniques and generalized $Γ$-calculus techniques. The advantages and drawbacks of each of these methods are discussed.

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…

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 …

New proof of Lie-Tresse theorem with computational advantages.

Proposes a new simulator for complex arrival processes.

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…

We replace the output layer of deep neural nets, typically the softmax function, by a novel interpolating function. And we propose end-to-end training and testing algorithms for this new architecture. Compared to classical neural nets with softmax function as output activation, the surrogate with interpolating function…

Quantum oracles help identify counterfactuals better than classical ones.

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

The paper explores multidimensional critic output in GANs, improving convergence and diversity.

Develops a method to efficiently use offline data for RL policy optimization.

Quantum algorithms accelerate financial risk computation.

New method learns disentangled discrete representations using categorical variational autoencoders.

Theoretical analysis of MCR for improving imputation quality in partially observed data.

Generating user interpretable multi-class predictions in data rich environments with many classes and explanatory covariates is a daunting task. We introduce Diagonal Orthant Latent Dirichlet Allocation (DOLDA), a supervised topic model for multi-class classification that can handle both many classes as well as many co…

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.

Single T-gate makes distribution learning hard for deep circuits.

This study improves quantum classifiers by optimizing data preprocessing.

Quantum circuits reveal pathways to dequantization in machine learning models.

Model-based clustering imposes a finite mixture modelling structure on data for clustering. Finite mixture models assume that the population is a convex combination of a finite number of densities, the distribution within each population is a basic assumption of each particular model. Among all distributions that have …