English
Related papers

Related papers: Complexity of randomized algorithms for underdampe…

200 papers

Log-concave sampling has witnessed remarkable algorithmic advances in recent years, but the corresponding problem of proving lower bounds for this task has remained elusive, with lower bounds previously known only in dimension one. In this…

Statistics Theory · Mathematics 2023-10-31 Sinho Chewi , Jaume de Dios Pont , Jerry Li , Chen Lu , Shyam Narayanan

Calculating averages with respect to multimodal probability distributions is often necessary in applications. Markov chain Monte Carlo (MCMC) methods to this end, which are based on time averages along a realization of a Markov process…

Methodology · Statistics 2023-07-24 M. Chak , T. Lelièvre , G. Stoltz , U. Vaes

We study the problem of learning multivariate log-concave densities with respect to a global loss function. We obtain the first upper bound on the sample complexity of the maximum likelihood estimator (MLE) for a log-concave density on…

Statistics Theory · Mathematics 2018-12-06 Timothy Carpenter , Ilias Diakonikolas , Anastasios Sidiropoulos , Alistair Stewart

In centralized, distributed, and federated learning with stochastic gradients and $n$ workers, it was recently shown that it is infeasible to find an $\varepsilon$-stationary point faster than $\tilde{\Omega}\left(\min\left\{\frac{d \kappa…

Optimization and Control · Mathematics 2026-05-11 Grigory Begunov , Alexander Tyurin

We prove lower bounds on the complexity of finding $\epsilon$-stationary points (points $x$ such that $\|\nabla f(x)\| \le \epsilon$) of smooth, high-dimensional, and potentially non-convex functions $f$. We consider oracle-based complexity…

Optimization and Control · Mathematics 2019-08-16 Yair Carmon , John C. Duchi , Oliver Hinder , Aaron Sidford

We lower bound the complexity of finding $\epsilon$-stationary points (with gradient norm at most $\epsilon$) using stochastic first-order methods. In a well-studied model where algorithms access smooth, potentially non-convex functions…

Optimization and Control · Mathematics 2022-03-01 Yossi Arjevani , Yair Carmon , John C. Duchi , Dylan J. Foster , Nathan Srebro , Blake Woodworth

Rerandomization is an experimental design technique that repeatedly randomizes treatment assignments until covariates are balanced between treatment groups. Rerandomization in the design stage of an experiment can lead to many asymptotic…

Methodology · Statistics 2026-04-10 Antônio Carlos Herling Ribeiro Junior

We present novel algorithms for simulation optimization using random directions stochastic approximation (RDSA). These include first-order (gradient) as well as second-order (Newton) schemes. We incorporate both continuous-valued as well as…

Optimization and Control · Mathematics 2015-08-11 Prashanth L. A. , Shalabh Bhatnagar , Michael Fu , Steve Marcus

It was recently shown in [4] that, for $L_2$-approximation of functions from a Hilbert space, function values are almost as powerful as arbitrary linear information, if the approximation numbers are square-summable. That is, we showed that…

Numerical Analysis · Mathematics 2023-05-15 Mario Ullrich

This paper addresses the challenge of solving Constrained Markov Decision Processes (CMDPs) with $d > 1$ constraints when the transition dynamics are unknown, but samples can be drawn from a generative model. We propose a model-based…

Machine Learning · Computer Science 2025-03-11 Max Buckley , Konstantinos Papathanasiou , Andreas Spanopoulos

Gradient-descent-based algorithms and their stochastic versions have widespread applications in machine learning and statistical inference. In this work we perform an analytic study of the performances of one of them, the Langevin…

We introduce a framework for Newton's flows in probability space with information metrics, named information Newton's flows. Here two information metrics are considered, including both the Fisher-Rao metric and the Wasserstein-2 metric. A…

Optimization and Control · Mathematics 2020-08-06 Yifei Wang , Wuchen Li

We give lower bounds on the performance of two of the most popular sampling methods in practice, the Metropolis-adjusted Langevin algorithm (MALA) and multi-step Hamiltonian Monte Carlo (HMC) with a leapfrog integrator, when applied to…

Data Structures and Algorithms · Computer Science 2021-10-28 Yin Tat Lee , Ruoqi Shen , Kevin Tian

Recent advances have significantly improved our understanding of the sample complexity of learning in average-reward Markov decision processes (AMDPs) under the generative model. However, much less is known about the constrained…

Machine Learning · Computer Science 2025-09-23 Yukuan Wei , Xudong Li , Lin F. Yang

We consider the problem of identifying the parameters of an unknown mixture of two arbitrary $d$-dimensional gaussians from a sequence of independent random samples. Our main results are upper and lower bounds giving a computationally…

Machine Learning · Computer Science 2015-05-19 Moritz Hardt , Eric Price

The randomized midpoint Langevin Monte Carlo (RLMC), introduced by Shen and Lee (2019), is a variant of classical Unadjusted Langevin Algorithm. It was shown in the literature that the RLMC is an efficient algorithm for approximating…

Statistics Theory · Mathematics 2025-11-18 Ruinan Li , Tian Shen , Zhonggen Su

This paper presents a lower bound for optimizing a finite sum of $n$ functions, where each function is $L$-smooth and the sum is $\mu$-strongly convex. We show that no algorithm can reach an error $\epsilon$ in minimizing all functions from…

Machine Learning · Statistics 2015-10-06 Alekh Agarwal , Leon Bottou

This paper presents a randomized algorithm for computing the near-optimal low-rank dynamic mode decomposition (DMD). Randomized algorithms are emerging techniques to compute low-rank matrix approximations at a fraction of the cost of…

Numerical Analysis · Mathematics 2019-11-28 N. Benjamin Erichson , Lionel Mathelin , Steven L. Brunton , J. Nathan Kutz

We study learning to learn for regression problems through the lens of hyperparameter tuning. We propose the Langevin Gradient Descent Algorithm (LGD), which approximates the mean of the posterior distribution defined by the loss function…

Machine Learning · Computer Science 2026-04-16 Saumya Goyal , Rohith Rongali , Ritabrata Ray , Barnabás Póczos

We investigate the problem of best-policy identification in discounted Markov Decision Processes (MDPs) when the learner has access to a generative model. The objective is to devise a learning algorithm returning the best policy as early as…

Machine Learning · Statistics 2021-05-11 Aymen Al Marjani , Alexandre Proutiere