English
Related papers

Related papers: Improved sample complexity bound for sample-based …

200 papers

Recently, there has been significant progress in understanding reinforcement learning in discounted infinite-horizon Markov decision processes (MDPs) by deriving tight sample complexity bounds. However, in many real-world applications, an…

Machine Learning · Statistics 2016-05-12 Christoph Dann , Emma Brunskill

Simulating open quantum systems is an essential technique for understanding complex physical phenomena and advancing quantum technologies. Some quantum algorithms simulate Lindblad dynamics exponentially accurately, i.e., they achieve…

Quantum Physics · Physics 2026-02-24 Jumpei Kato , Kaito Wada , Kosuke Ito , Naoki Yamamoto

It has been experimentally observed in recent years that multi-layer artificial neural networks have a surprising ability to generalize, even when trained with far more parameters than observations. Is there a theoretical basis for this?…

Machine Learning · Statistics 2018-09-19 Andrew R. Barron , Jason M. Klusowski

Trotter decomposition provides a simple approach to simulating open quantum systems by decomposing the Lindbladian into a sum of individual terms. While it is established that Trotter errors in Hamiltonian simulation depend on nested…

Quantum Physics · Physics 2026-03-31 Xinzhao Wang , Shuo Zhou , Xiaoyang Wang , Yi-Cong Zheng , Shengyu Zhang , Tongyang Li

In this paper, we introduce a novel and general framework for the variational quantum simulation of Lindblad equations. Building on the close relationship between the unraveled Lindblad dynamics, stochastic Magnus integrators, and…

Quantum Physics · Physics 2025-09-22 Jia-Cheng Huang , Hao-En Li , Yi-Cheng Wang , Guang-Ze Zhang , Jun Li , Han-Shi Hu

The simplex method for linear programming is known to be highly efficient in practice, and understanding its performance from a theoretical perspective is an active research topic. The framework of smoothed analysis, first introduced by…

Data Structures and Algorithms · Computer Science 2025-10-22 Sophie Huiberts , Yin Tat Lee , Xinzhi Zhang

In this study, we derive Probably Approximately Correct (PAC) bounds on the asymptotic sample-complexity for RL within the infinite-horizon Markov Decision Process (MDP) setting that are sharper than those in existing literature. The…

Machine Learning · Computer Science 2025-07-17 Mohit Prashant , Arvind Easwaran

We establish an information complexity lower bound of randomized algorithms for simulating underdamped Langevin dynamics. More specifically, we prove that the worst $L^2$ strong error is of order $\Omega(\sqrt{d}\, N^{-3/2})$, for solving a…

Numerical Analysis · Mathematics 2022-05-10 Yu Cao , Jianfeng Lu , Lihan Wang

In this paper, we present near-optimal space bounds for Lp-samplers. Given a stream of updates (additions and subtraction) to the coordinates of an underlying vector x \in R^n, a perfect Lp sampler outputs the i-th coordinate with…

Data Structures and Algorithms · Computer Science 2010-12-23 Hossein Jowhari , Mert Sağlam , Gábor Tardos

Simulating the dynamics of open quantum systems is a crucial task in quantum computing, offering wide-ranging applications but remaining computationally challenging. In this paper, we propose two quantum algorithms for simulating the…

Quantum Physics · Physics 2025-10-29 Sirui Peng , Xiaoming Sun , Qi Zhao , Hongyi Zhou

Given a data matrix $X \in R^{n\times d}$ and a response vector $y \in R^{n}$, suppose $n>d$, it costs $O(n d^2)$ time and $O(n d)$ space to solve the least squares regression (LSR) problem. When $n$ and $d$ are both large, exactly solving…

Machine Learning · Computer Science 2014-04-08 Shusen Wang

This paper studies sampling error bounds for denoising diffusion probabilistic models (DDPMs) in the 2-Wasserstein distance. Our contributions are threefold. (i) Under general Lipschitz-type conditions on the score function and for a broad…

Machine Learning · Statistics 2026-05-19 Yuta Koike

We prove optimal sampling bounds achieving $(1\pm\varepsilon)$-relative error for a broad class of Lipschitz continuous classification loss functions under various regularization terms. This includes important functions such as logistic and…

Machine Learning · Computer Science 2026-05-25 Meysam Alishahi , Alexander Munteanu , Simon Omlor , Jeff M. Phillips

We rigorously quantify the improvement in the sample complexity of variational divergence estimations for group-invariant distributions. In the cases of the Wasserstein-1 metric and the Lipschitz-regularized $\alpha$-divergences, the…

Statistics Theory · Mathematics 2024-11-26 Ziyu Chen , Markos A. Katsoulakis , Luc Rey-Bellet , Wei Zhu

Lindblad dynamics and other open-system dynamics provide a promising path towards efficient Gibbs sampling on quantum computers. In these proposals, the Lindbladian is obtained via an algorithmic construction akin to designing an artificial…

Quantum Physics · Physics 2025-03-07 Zhiyan Ding , Bowen Li , Lin Lin

Away from equilibrium, the properties of open quantum systems depend on the details of their environment. A microscopic derivation of a master equation (ME) is therefore crucial. Of particular interest are Lindblad-type equations, not only…

Quantum Physics · Physics 2021-07-14 Tobias Becker , Ling-Na Wu , André Eckardt

We propose a method for solving the Jalilian-Marian-Iancu-McLerran-Weigert-Leonidov-Kovner (JIMWLK) evolution equation on quantum computers. Our approach exploits the reformulation of the JIMWLK equation as a Lindblad master equation…

High Energy Physics - Phenomenology · Physics 2026-03-04 Anjali A. Agrawal , Evan Budd , Alexander F. Kemper , Vladimir V. Skokov , Andrey Tarasov , Shaswat Tiwari

This paper studies sample average approximation (SAA) in solving convex or strongly convex stochastic programming (SP) problems. In estimating SAA's sample efficiency, the state-of-the-art sample complexity bounds entail metric entropy…

Optimization and Control · Mathematics 2026-03-03 Hongcheng Liu , Jindong Tong

Analog Quantum Simulators offer a route to exploring strongly correlated many-body dynamics beyond classical computation, but their predictive power remains limited by the absence of quantitative error estimation. Establishing rigorous…

We establish sample complexity results for stochastic optimization over the integers, especially with a view to understand the complexity with respect to the corresponding continuous optimization problem. We show that integer optimization…

Machine Learning · Computer Science 2026-05-11 Hongyu Cheng , Yinghao Zheng , Marco Molinaro , Amitabh Basu