arXiv research

This paper optimizes sampling for least-squares approximation.

Proposes sampling from reverse diffusion posteriors for contextual bandits.

Stochastic gradient descent optimizes Nyström samples for kernel matrix approximation.

Sampling strategies significantly affect feature approximations in ELA, impacting classifier accuracy.

New method approximates CVaR with less data for heavy-tailed risks.

Study approximates unknown function levels with queries.

Paper proposes an algorithm to optimize CVaR using retrospective approximation and importance sampling.

We propose a novel approximate inference algorithm that approximates a target distribution by amortising the dynamics of a user-selected MCMC sampler. The idea is to initialise MCMC using samples from an approximation network, apply the MCMC operator to improve these samples, and finally use the samples to update the a…

Improved sample complexity for Gaussian process approximations.

VITS improves Thompson Sampling for contextual bandits with efficient approximate inference.

New sampling-based approach for filtering problems using multiplicative Gaussian functions.

New model OPSS allows constant approximation for maximum coverage problem.

New sampling methods improve Shapley values for explaining machine learning predictions.

Random sampling has become a critical tool in solving massive matrix problems. For linear regression, a small, manageable set of data rows can be randomly selected to approximate a tall, skinny data matrix, improving processing time significantly. For theoretical performance guarantees, each row must be sampled with pr…

New study shows exponential sample growth for ReQU neural networks.

Posterior refinement improves sample efficiency in Bayesian neural networks.

Recent advances in deep reinforcement learning have made significant strides in performance on applications such as Go and Atari games. However, developing practical methods to balance exploration and exploitation in complex domains remains largely unsolved. Thompson Sampling and its extension to reinforcement learning…

AAS optimizes neural network PDE approximations by adaptively sampling.

We study the problem of column selection in large-scale kernel canonical correlation analysis (KCCA) using the Nyström approximation, where one approximates two positive semi-definite kernel matrices using "landmark" points from the training set. When building low-rank kernel approximations in KCCA, previous work mostl…

New methods stabilize Q-learning with linear approximations.

New MCMC algorithm reduces subset selection passes to 2 for optimal $k$-dimensional subspace approximation.

New method estimates nested expectations with biased and antithetic sampling.

Improved Thompson sampling for bandits with Langevin algorithms.

VISA improves inference efficiency for complex models.

We give the first algorithm for kernel Nyström approximation that runs in *linear time in the number of training points* and is provably accurate for all kernel matrices, without dependence on regularity or incoherence conditions. The algorithm projects the kernel onto a set of $s$ landmark points sampled by their *rid…

This work improves sample efficiency in neural function approximation for reinforcement learning.

Improved bounds for function approximation in nonlinear sets.

Algorithm samples from Bingham distribution efficiently.

New method uses PDMPs with sub-sampling for efficient sampling from posterior distributions.

This work analyzes nonexpansive stochastic approximations with Markovian noise, proving convergence in reinforcement learning.

Uniform TD(0) bound derived for function approximation with Markov noise.

For optimization on large-scale data, exactly calculating its solution may be computationally difficulty because of the large size of the data. In this paper we consider subsampled optimization for fast approximating the exact solution. In this approach, one gets a surrogate dataset by sampling from the full data, and …

Ensemble sampling approximates Thompson sampling for complex models.

Improved predictive posterior density estimation through optimized importance sampling.

SIFT reduces training time by selecting samples with approximate losses.

SRF improves kernel approximation and GP regression performance.

This paper analyzes momentum Q-learning with finite-sample guarantees.

A new algorithm approximates logistic regression probabilities efficiently.

Efficiently simulates SABR model with novel sampling methods.

Study on distributional TD learning with linear approximations for better return estimation.

Many machine learning frameworks, such as resource-allocating networks, kernel-based methods, Gaussian processes, and radial-basis-function networks, require a sparsification scheme in order to address the online learning paradigm. For this purpose, several online sparsification criteria have been proposed to restrict …

We consider variants of trust-region and cubic regularization methods for non-convex optimization, in which the Hessian matrix is approximated. Under mild conditions on the inexact Hessian, and using approximate solution of the corresponding sub-problems, we provide iteration complexity to achieve $ε$-approximate seco…

Unified framework for sampling and approximating high-dimensional energy landscapes.

Improved sampling for high-dimensional posteriors with underdamped Langevin.

We study the effects of approximate inference on the performance of Thompson sampling in the $k$-armed bandit problems. Thompson sampling is a successful algorithm for online decision-making but requires posterior inference, which often must be approximated in practice. We show that even small constant inference error …

Matrix multiplication is a fundamental building block for large scale computations arising in various applications, including machine learning. There has been significant recent interest in using coding to speed up distributed matrix multiplication, that are robust to stragglers (i.e., machines that may perform slower …

Diverse sampling improves kernel methods' performance in sparse regions.

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…