arXiv research

Study nearest-neighbor radii under dependent sampling, finding they remain informative.

Study shows DQN's performance degrades with temporal dependence in data.

The K-sample testing problem involves determining whether K groups of data points are each drawn from the same distribution. Analysis of variance is arguably the most classical method to test mean differences, along with several recent methods to test distributional differences. In this paper, we demonstrate the existe…

DMLE improves active learning by correcting MLE for sample dependencies.

Efficiently selects top-m designs for various contexts using sequential sampling.

The paper considers the block sampling method for long-range dependent processes. Our theory generalizes earlier ones by Hall, Jing and Lahiri (1998) on functionals of Gaussian processes and Nordman and Lahiri (2005) on linear processes. In particular, we allow nonlinear transforms of linear processes. Under suitable c…

Paper proposes a new DR estimator for adaptive experiments with improved performance.

This paper improves dependency networks using information geometry.

Estimating the strength of dependency between two variables is fundamental for exploratory analysis and many other applications in data mining. For example: non-linear dependencies between two continuous variables can be explored with the Maximal Information Coefficient (MIC); and categorical variables that are depende…

Paper provides GOT convergence guarantees for sub-gamma distributions and dependent samples.

Optimizes quadratic bandits with tight Hessian-dependent sample complexity bounds.

CoT improves transformer sample efficiency by reducing input token dependencies and attention sparsity.

Copula Discrepancy benchmarks sample dependence structure against known families.

A new nonparametric test measures dependence between variables using decision trees.

A new sampling method balances multi-label datasets by preserving category frequency order.

Paper extends nonparametric regression bounds for dependent $\beta$-mixing samples.

Motivation: Algorithms that discover variables which are causally related to a target may inform the design of experiments. With observational gene expression data, many methods discover causal variables by measuring each variable's degree of statistical dependence with the target using dependence measures (DMs). Howev…

Study compares LRMC algorithms under dependent sampling in various applications.

Study improves sampling from non-log-concave distributions using Fisher information.

The paper explains why estimating a history-dependent policy can reduce MSE in reinforcement learning.

New algorithm learns optimal policies with just 1 episode, settling horizon-dependence in RL.

Differential privacy of Gaussian process posterior sampling

Paper addresses OPE for dependent bandit samples using MDS and batch updates.

New RNN model handles long-term dependencies in irregularly-sampled time series.

We develop a new method to estimate failure probabilities in complex systems.

Paper proposes method for generating paths of stochastic volatility CGMY process for option pricing.

This paper analyzes RMR under Markov-dependent samples, improving understanding of its generalization error.

In this paper, we consider the problem of column subset selection. We present a novel analysis of the spectral norm reconstruction for a simple randomized algorithm and establish a new bound that depends explicitly on the sampling probabilities. The sampling dependent error bound (i) allows us to better understand the …

Identifying dependency in multivariate data is a common inference task that arises in numerous applications. However, existing nonparametric independence tests typically require computation that scales at least quadratically with the sample size, making it difficult to apply them to massive data. Moreover, resampling i…

CORES2 removes noisy labels by sieving out corrupted examples.

Random features provide a practical framework for large-scale kernel approximation and supervised learning. It has been shown that data-dependent sampling of random features using leverage scores can significantly reduce the number of features required to achieve optimal learning bounds. Leverage scores introduce an op…

Proves minimax sample complexity for turn-based stochastic games.

Proposes a method to estimate time-dependent probability density functions using binary classifiers.

New bounds show limitations of sample-wise information-theoretic generalization.

We revisit the inductive matrix completion problem that aims to recover a rank-$r$ matrix with ambient dimension $d$ given $n$ features as the side prior information. The goal is to make use of the known $n$ features to reduce sample and computational complexities. We present and analyze a new gradient-based non-convex…

Paper reduces sample complexity for bilinear systems identification to nearly constant.

We consider PAC-learning a good item from $k$-subsetwise feedback information sampled from a Plackett-Luce probability model, with instance-dependent sample complexity performance. In the setting where subsets of a fixed size can be tested and top-ranked feedback is made available to the learner, we give an algorithm w…

New RL method reduces sample complexity for large policy spaces.

This paper examines quantile dependence between international stock markets and evaluates its use for improving volatility forecasting. First, we analyze quantile dependence and directional predictability between the US stock market and stock markets in the UK, Germany, France and Japan. We use the cross-quantilogram, …

Are expansions and recessions more likely to end as their magnitude increases? In this paper we apply parametric hazard models to investigate this issue in a sample of 16 countries from 1881 to 2000. For the total sample we find evidence of positive magnitude dependence for recessions, while for expansions we are not a…

GMMNs model cross-sectional dependence for better option pricing and simulation.

A new method simplifies sampling from complex distributions without using diffusions.

Meta-learners improve causal effect estimation in small samples.

New reinforcement learning algorithm achieves instance-optimal sample complexity.

CDSSL improves representation quality by integrating linear and nonlinear dependencies.

New method uncovers zero entropy in dependent observations after finite samples.

New method for cross-validation in high-dimensional data with dependent or heavy-tailed covariates.

Study on learning properties of scale-dependent kernels controlling stability and error.