Zobrazeno 1 - 10
of 324
pro vyhledávání: '"Rinaldo D'Alessandro"'
Statistical inference with finite-sample validity for the value function of a given policy in Markov decision processes (MDPs) is crucial for ensuring the reliability of reinforcement learning. Temporal Difference (TD) learning, arguably the most wid
Externí odkaz:
http://arxiv.org/abs/2410.16106
Diffusion models have emerged as a powerful tool for image generation and denoising. Typically, generative models learn a trajectory between the starting noise distribution and the target data distribution. Recently Liu et al. (2023b) designed a nove
Externí odkaz:
http://arxiv.org/abs/2410.14949
The softmax gating function is arguably the most popular choice in mixture of experts modeling. Despite its widespread use in practice, the softmax gating may lead to unnecessary competition among experts, potentially causing the undesirable phenomen
Externí odkaz:
http://arxiv.org/abs/2405.13997
Mixture of experts (MoE) model is a statistical machine learning design that aggregates multiple expert networks using a softmax gating function in order to form a more intricate and expressive model. Despite being commonly used in several applicatio
Externí odkaz:
http://arxiv.org/abs/2402.02952
The prevailing statistical approach to analyzing persistence diagrams is concerned with filtering out topological noise. In this paper, we adopt a different viewpoint and aim at estimating the actual distribution of a random persistence diagram, whic
Externí odkaz:
http://arxiv.org/abs/2310.11982
We consider the problem of inference for projection parameters in linear regression with increasing dimensions. This problem has been studied under a variety of assumptions in the literature. The classical asymptotic normality result for the least sq
Externí odkaz:
http://arxiv.org/abs/2307.00795
We study the multilayer random dot product graph (MRDPG) model, an extension of the random dot product graph to multilayer networks. To estimate the edge probabilities, we deploy a tensor-based methodology and demonstrate its superiority over existin
Externí odkaz:
http://arxiv.org/abs/2306.15286
We derive novel and sharp high-dimensional Berry--Esseen bounds for the sum of $m$-dependent random vectors over the class of hyper-rectangles exhibiting only a poly-logarithmic dependence in the dimension. Our results hold under minimal assumptions,
Externí odkaz:
http://arxiv.org/abs/2306.14299
This paper is concerned with the problem of policy evaluation with linear function approximation in discounted infinite horizon Markov decision processes. We investigate the sample complexities required to guarantee a predefined estimation error of t
Externí odkaz:
http://arxiv.org/abs/2305.19001
We develop a novel, general and computationally efficient framework, called Divide and Conquer Dynamic Programming (DCDP), for localizing change points in time series data with high-dimensional features. DCDP deploys a class of greedy algorithms that
Externí odkaz:
http://arxiv.org/abs/2301.10942