arXiv research

An algorithm solves optimization problems with large sample sets, improving worst-case complexity.

Unified sampling approach for Bayesian imaging problems.

MOTS improves Thompson sampling to match minimax bounds for bandit problems.

Optimizes sample weights for representative data averages.

Sampling is a fundamental problem in computer science and statistics. However, for a given task and stream, it is often not possible to choose good sampling probabilities in advance. We derive a general framework for adaptively changing the sampling probabilities via a collection of thresholds.In general, adaptive samp…

Diffusion models tackle noisy inverse problems with posterior sampling.

Drawing a sample from a discrete distribution is one of the building components for Monte Carlo methods. Like other sampling algorithms, discrete sampling suffers from the high computational burden in large-scale inference problems. We study the problem of sampling a discrete random variable with a high degree of depen…

This paper shows using sub-sample estimates can improve optimization results in large-scale problems.

Improved diffusion sampling for inverse problems with faster and more robust inference.

New method solves linear inverse problems using diffusion models.

Flow Annealing Posterior Sampling unifies stochastic-process regression and PDE inverse problems.

Optimizes Thompson sampling policies using policy gradient methods.

Paper proposes efficient algorithms for bandit problems with costly sampling.

Ensemble sampling approximates Thompson sampling for complex models.

We present an embedding of stochastic optimal control problems, of the so called path integral form, into reproducing kernel Hilbert spaces. Using consistent, sample based estimates of the embedding leads to a model free, non-parametric approach for calculation of an approximate solution to the control problem. This fo…

The problem of drawing samples from a discrete distribution can be converted into a discrete optimization problem. In this work, we show how sampling from a continuous distribution can be converted into an optimization problem over continuous space. Central to the method is a stochastic process recently described in ma…

New model OPSS allows constant approximation for maximum coverage problem.

We formulate the problem of sampling and recovering clustered graph signal as a multi-armed bandit (MAB) problem. This formulation lends naturally to learning sampling strategies using the well-known gradient MAB algorithm. In particular, the sampling strategy is represented as a probability distribution over the indiv…

New Thompson sampling algorithm for stochastic partial monitoring achieves logarithmic regret.

The paper explores sampling problems and shows minimal exploration is needed.

Thompson sampling provides a solution to bandit problems in which new observations are allocated to arms with the posterior probability that an arm is optimal. While sometimes easy to implement and asymptotically optimal, Thompson sampling can be computationally demanding in large scale bandit problems, and its perform…

Localized sampler tackles high-dimensional sampling with fewer samples.

D-Wave computers struggle with sampling Boltzmann distributions efficiently.

A new method for sampling complex posterior distributions in DDMs.

RePS improves diffusion models for solving inverse problems efficiently.

Paper resolves open problems on sample complexity in binary hypothesis testing.

This paper is concerned with the problem of low rank plus sparse matrix decomposition for big data. Conventional algorithms for matrix decomposition use the entire data to extract the low-rank and sparse components, and are based on optimization problems with complexity that scales with the dimension of the data, which…

New BE dimension measure reveals rich RL problems with sample-efficient algorithms.

Improved sampling for high-dimensional posteriors with underdamped Langevin.

Many data-fitting applications require the solution of an optimization problem involving a sum of large number of functions of high dimensional parameter. Here, we consider the problem of minimizing a sum of $n$ functions over a convex constraint set $\mathcal{X} \subseteq \mathbb{R}^{p}$ where both $n$ and $p$ are lar…

This article reviews and explains HMC-based methods for sampling constrained continuous distributions.

The two-sample hypothesis testing problem is studied for the challenging scenario of high dimensional data sets with small sample sizes. We show that the two-sample hypothesis testing problem can be posed as a one-class set classification problem. In the set classification problem the goal is to classify a set of data …

The SPS method constructs confidence regions for true parameters with optimal sample complexity.

Private optimization faster on interpolation problems with quadratic growth.

Improves sampling, rounding, and integration of logconcave functions.

Study private query release with public data, reducing sample sizes.

Paper introduces a new sampling method for Bayesian inference.

Improved Thompson Sampling reduces regret in contextual bandits and reinforcement learning.

SGD improves DR by solving two-stage sampling problems.

Thompson sampling used for linear bandits with normal-gamma priors.

Leverage score sampling provides an appealing way to perform approximate computations for large matrices. Indeed, it allows to derive faithful approximations with a complexity adapted to the problem at hand. Yet, performing leverage scores sampling is a challenge in its own right requiring further approximations. In th…

We examine a fundamental problem that models various active sampling setups, such as network tomography. We analyze sampling of a multivariate normal distribution with an unknown expectation that needs to be estimated: in our setup it is possible to sample the distribution from a given set of linear functionals, and th…

Robust support vector machine (RSVM) has been shown to perform remarkably well to improve the generalization performance of support vector machine under the noisy environment. Unfortunately, in order to handle the non-convexity induced by ramp loss in RSVM, existing RSVM solvers often adopt the DC programming framework…

New method improves posterior sampling for complex data models.

Algorithm samples from Bingham distribution efficiently.

New algorithms for sampling in constrained domains without learning rates.

Two statistical tasks are shown to have equivalent sample complexity.

Enhances Bayesian model selection for high-dimensional problems.