arXiv research

New oracles improve stochastic optimization with noisy or biased measurements.

This paper establishes non-asymptotic oracle inequalities for the prediction error and estimation accuracy of the LASSO in stationary vector autoregressive models. These inequalities are used to establish consistency of the LASSO even when the number of parameters is of a much larger order of magnitude than the sample …

New algorithms sample convex bodies using Markov chains and restricted Gaussian oracles.

Develops accelerated fixed-point methods with delayed oracles for scientific computing.

Extends covariance estimation with multiple targets for better performance.

Two important goals of high-dimensional modeling are prediction and variable selection. In this article, we consider regularization with combined $L_1$ and concave penalties, and study the sampling properties of the global optimum of the suggested method in ultra-high dimensional settings. The $L_1$-penalty provides th…

We consider the estimation of two-sample integral functionals, of the type that occur naturally, for example, when the object of interest is a divergence between unknown probability densities. Our first main result is that, in wide generality, a weighted nearest neighbour estimator is efficient, in the sense of achievi…

Derives error formula for convex regression in high dimensions.

High-dimensional data analysis has motivated a spectrum of regularization methods for variable selection and sparse modeling, with two popular classes of convex ones and concave ones. A long debate has been on whether one class dominates the other, an important question both in theory and to practitioners. In this pape…

Riemannian Proximal Sampler improves sampling on manifold data.

We consider the finite sample properties of the regularized high-dimensional Cox regression via lasso. Existing literature focuses on linear models or generalized linear models with Lipschitz loss functions, where the empirical risk functions are the summations of independent and identically distributed (iid) losses. T…

The paper improves count data regression models for overdispersed data.

Unified framework for understanding GRPO as U-statistic.

The paper addresses nonconvex penalized LAD estimation in partial linear models using DNNs.

New weighted Lasso estimates improve logistic regression performance with measurement error.

This paper consider penalized empirical loss minimization of convex loss functions with unknown non-linear target functions. Using the elastic net penalty we establish a finite sample oracle inequality which bounds the loss of our estimator from above with high probability. If the unknown target is linear this inequali…

High throughput genetic sequencing arrays with thousands of measurements per sample and a great amount of related censored clinical data have increased demanding need for better measurement specific model selection. In this paper we establish strong oracle properties of nonconcave penalized methods for nonpolynomial (N…

We presented Bayesian portfolio selection strategy, via the $k$ factor asset pricing model. If the market is information efficient, the proposed strategy will mimic the market; otherwise, the strategy will outperform the market. The strategy depends on the selection of a portfolio via Bayesian multiple testing methodol…

EP-learning framework improves causal contrast estimation efficiency.

Propose an XMSE-aware mixed estimator for EB that interpolates between ML and EB shrinkage.

The effect of errors in variables in quantization is investigated. We prove general exact and non-exact oracle inequalities with fast rates for an empirical minimization based on a noisy sample $Z_i=X_i+ε_i,i=1,\ldots,n$, where $X_i$ are i.i.d. with density $f$ and $ε_i$ are i.i.d. with density $η$. These rates depend …

New analysis reveals optimal regularization for ESNs, avoiding double descent.

New model-free RL algorithm tackles robust average-reward problems with finite sample complexity analysis.

The paper addresses model averaging and ensembling, providing theoretical and practical insights.

ERM performs well in feature learning with minimal feature maps.

Develops asymptotic theory for deep Cox models to enable valid inference.

We study the asymptotic properties of the adaptive Lasso in cointegration regressions in the case where all covariates are weakly exogenous. We assume the number of candidate I(1) variables is sub-linear with respect to the sample size (but possibly larger) and the number of candidate I(0) variables is polynomial with …

Improved GANs estimate convergence rate for density estimation.

Algorithm minimizes regret while adhering to unknown safety constraints.

New algorithm explores optimally using same primitives as Thompson Sampling.

New algorithm optimizes stochastic optimization with circular dependency.

New model handles complex non-linear relationships with hidden graph structures.

Paper proposes CIV estimator for categorical instruments in small sample settings.

Given the observation of a high-dimensional Ornstein-Uhlenbeck (OU) process in continuous time, we proceed to the inference of the drift parameter under a row-sparsity assumption. Towards that aim, we consider the negative log-likelihood of the process, penalized by an $\ell^1$-penalization (Lasso and Adaptive Lasso). …

New tool for parallel and private stochastic convex optimization reduces query complexity.

Oracle-efficient algorithms reduce combinatorial semi-bandit regret to logarithmic time.

New GIC improves model selection for structured sparse models.

We propose a new sparsity-smoothness penalty for high-dimensional generalized additive models. The combination of sparsity and smoothness is crucial for mathematical theory as well as performance for finite-sample data. We present a computationally efficient algorithm, with provable numerical convergence properties, fo…

New algorithm improves materials discovery using max K-Armed Bandit.

New analysis shows Thompson Sampling can work with greedy approximations in combinatorial bandits.

TA-CQR predicts regression intervals with exact coverage, splitting miscoverage between endpoints.

MAMBA learns policies competitive with multiple conflicting oracles.

We study the problem of interactively learning a binary classifier using noisy labeling and pairwise comparison oracles, where the comparison oracle answers which one in the given two instances is more likely to be positive. Learning from such oracles has multiple applications where obtaining direct labels is harder bu…

Adaptive importance sampling (AIS) uses past samples to update the \textit{sampling policy} $q_t$ at each stage $t$. Each stage $t$ is formed with two steps : (i) to explore the space with $n_t$ points according to $q_t$ and (ii) to exploit the current amount of information to update the sampling policy. The very funda…

A new method solves variational inequality problems with multiple constraints without needing optimal Lagrange multipliers.

In most classification tasks there are observations that are ambiguous and therefore difficult to correctly label. Set-valued classifiers output sets of plausible labels rather than a single label, thereby giving a more appropriate and informative treatment to the labeling of ambiguous instances. We introduce a framewo…

New oracle uses uncertainty for active classification with noisy feedback.

Quantum oracles help identify counterfactuals better than classical ones.