English
Related papers

Related papers: High-probability minimax lower bounds

200 papers

We study online convex optimization under stochastic sub-gradient observation faults, where we introduce adaptive algorithms with minimax optimal regret guarantees. We specifically study scenarios where our sub-gradient observations can be…

Machine Learning · Computer Science 2019-04-23 Hakan Gokcesu , Suleyman S. Kozat

Gaussian random vectors exhibit the loss of dimension phenomena, which relate to their joint survival tail behaviour. Besides, the fact that the components of such vectors are light-tailed complicates the approximations of various…

Risk Management · Quantitative Finance 2018-10-09 E. Hashorva

This paper introduces the partial Gini covariance, a novel dependence measure that addresses the challenges of high-dimensional inference with heavy-tailed errors, often encountered in fields like finance, insurance, climate, and biology.…

Methodology · Statistics 2024-11-21 Yilin Zhang , Songshan Yang , Yunan Wu , Lan Wang

For a risk vector $V$, whose components are shared among agents by some random mechanism, we obtain asymptotic lower and upper bounds for the individual agents' exposure risk and the aggregated risk in the market. Risk is measured by…

Risk Management · Quantitative Finance 2016-04-12 Oliver Kley , Claudia Kluppelberg

High-dimensional models often have a large memory footprint and must be quantized after training before being deployed on resource-constrained edge devices for inference tasks. In this work, we develop an information-theoretic framework for…

Information Theory · Computer Science 2022-09-01 Rajarshi Saha , Mert Pilanci , Andrea J. Goldsmith

A general lower bound is developed for the minimax risk when estimating an arbitrary functional. The bound is based on testing two composite hypotheses and is shown to be effective in estimating the nonsmooth functional…

Statistics Theory · Mathematics 2011-05-17 T. Tony Cai , Mark G. Low

Given a task of predicting $Y$ from $X$, a loss function $L$, and a set of probability distributions $\Gamma$ on $(X,Y)$, what is the optimal decision rule minimizing the worst-case expected loss over $\Gamma$? In this paper, we address…

Machine Learning · Statistics 2017-07-05 Farzan Farnia , David Tse

Tensor regression is an important tool for tensor data analysis, but existing works have not considered the impact of outliers, making them potentially sensitive to such data points. This paper proposes a low tubal rank robust regression…

Methodology · Statistics 2026-05-11 Zihao Song , Jicai Liu , Heng Lian , Weihua Zhao

Rejection Sampling is a fundamental Monte-Carlo method. It is used to sample from distributions admitting a probability density function which can be evaluated exactly at any given point, albeit at a high computational cost. However,…

Machine Learning · Statistics 2018-10-23 Juliette Achdou , Joseph C. Lam , Alexandra Carpentier , Gilles Blanchard

A wide array of machine learning problems are formulated as the minimization of the expectation of a convex loss function on some parameter space. Since the probability distribution of the data of interest is usually unknown, it is is often…

Optimization and Control · Mathematics 2019-05-27 Emilie Chouzenoux , Henri Gérard , Jean-Christophe Pesquet

The well-known "Janson's inequality" gives Poisson-like upper bounds for the lower tail probability \Pr(X \le (1-\eps)\E X) when X is the sum of dependent indicator random variables of a special form. We show that, for large deviations,…

Probability · Mathematics 2017-12-12 Svante Janson , Lutz Warnke

It is a common phenomenon that for high-dimensional and nonparametric statistical models, rate-optimal estimators balance squared bias and variance. Although this balancing is widely observed, little is known whether methods exist that…

Statistics Theory · Mathematics 2023-03-21 Alexis Derumigny , Johannes Schmidt-Hieber

Gradient clipping is a commonly used technique to stabilize the training process of neural networks. A growing body of studies has shown that gradient clipping is a promising technique for dealing with the heavy-tailed behavior that emerged…

Machine Learning · Computer Science 2023-07-26 Shaojie Li , Yong Liu

We derive upper bounds on the tail conditional expectation of binomial and Poisson random variables. Those upper bounds are subsequently employed to the problem of obtaining non-asymptotic lower bounds on the probability that the…

Probability · Mathematics 2017-12-07 Christos Pelekis

We propose a framework for computing, optimizing and integrating with respect to a smooth marginal likelihood in statistical models that involve high-dimensional parameters/latent variables and continuous low-dimensional hyperparameters.…

Methodology · Statistics 2026-02-10 Omiros Papaspiliopoulos , Timothée Stumpf-Fétizon , Jonathan Weare

We present the first minimax risk bounds for estimators of the spectral measure in multivariate linear factor models, where observations are linear combinations of regularly varying latent factors. Non-asymptotic convergence rates are…

Statistics Theory · Mathematics 2024-11-12 Xuhui Zhang , Jose Blanchet , Youssef Marzouk , Viet Anh Nguyen , Sven Wang

We propose a residual randomization procedure designed for robust Lasso-based inference in the high-dimensional setting. Compared to earlier work that focuses on sub-Gaussian errors, the proposed procedure is designed to work robustly in…

Methodology · Statistics 2021-08-20 Y. Samuel Wang , Si Kai Lee , Panos Toulis , Mladen Kolar

We consider non-convex stochastic optimization using first-order algorithms for which the gradient estimates may have heavy tails. We show that a combination of gradient clipping, momentum, and normalized gradient descent yields convergence…

Machine Learning · Computer Science 2021-11-10 Ashok Cutkosky , Harsh Mehta

We derive lower bounds on the Bayes risk in decentralized estimation, where the estimator does not have direct access to the random samples generated conditionally on the random parameter of interest, but only to the data received from…

Information Theory · Computer Science 2016-07-05 Aolin Xu , Maxim Raginsky

The popularity of penalized regression in high-dimensional data analysis has led to a demand for new inferential tools for these models. False discovery rate control is widely used in high-dimensional hypothesis testing, but has only…

Methodology · Statistics 2019-01-24 Ryan Miller , Patrick Breheny
‹ Prev 1 4 5 6 7 8 10 Next ›