English
Related papers

Related papers: On Invariance Penalties for Risk Minimization

200 papers

We study the problem of estimating Dynamic Discrete Choice (DDC) models, also known as offline Maximum Entropy-Regularized Inverse Reinforcement Learning (offline MaxEnt-IRL) in machine learning. The objective is to recover reward or $Q^*$…

Machine Learning · Computer Science 2026-05-06 Enoch H. Kang , Hema Yoganarasimhan , Lalit Jain

The goal of the inverse reinforcement learning (IRL) problem is to recover the reward functions from expert demonstrations. However, the IRL problem like any ill-posed inverse problem suffers the congenital defect that the policy may be…

Machine Learning · Computer Science 2022-09-26 Ce Ju

Rerandomization utilizes modern computing ability to improve covariate balance while adhering to the randomization principle originally advocated by RA Fisher. Affinely invariant rerandomization has the ``Equal Percent Variance Reducing''…

Methodology · Statistics 2025-04-03 Zhen Zhong , Donald B. Rubin

Machine unlearning offers a promising solution to privacy and safety concerns in large language models (LLMs) by selectively removing targeted knowledge while preserving utility. However, current methods are highly sensitive to downstream…

The weight decay regularization term is widely used during training to constrain expressivity, avoid overfitting, and improve generalization. Historically, this concept was borrowed from the SVM maximum margin principle and extended to…

Machine Learning · Computer Science 2021-10-12 Berry Weinstein , Shai Fine , Yacov Hel-Or

In order to model risk aversion in reinforcement learning, an emerging line of research adapts familiar algorithms to optimize coherent risk functionals, a class that includes conditional value-at-risk (CVaR). Because optimizing the…

Machine Learning · Computer Science 2021-03-09 Audrey Huang , Liu Leqi , Zachary C. Lipton , Kamyar Azizzadenesheli

We introduce an innovative approach to enhancing the empirical risk minimization (ERM) process in model training through a refined reweighting scheme of the training data to enhance fairness. This scheme aims to uphold the sufficiency rule…

Machine Learning · Computer Science 2024-10-02 Xuan Zhao , Klaus Broelemann , Salvatore Ruggieri , Gjergji Kasneci

Inverse reinforcement learning (IRL) for linear systems seeks a cost function whose optimal controller reproduces an expert policy from data. Existing data-driven methods for discrete-time linear systems are largely built on iterative…

Systems and Control · Electrical Eng. & Systems 2026-05-12 Duc Cuong Nguyen , Phuong Nam Dao

In this paper, we address the issue of model specification in probabilistic latent variable models (PLVMs) using an infinite-horizon optimal control approach. Traditional PLVMs rely on joint distributions to model complex data, but…

Systems and Control · Electrical Eng. & Systems 2025-07-29 Zhichao Chen , Hao Wang , Licheng Pan , Yiran Ma , Yunfei Teng , Jiaze Ma , Le Yao , Zhiqiang Ge , Zhihuan Song

Machine learning models have exhibited exceptional results in various domains. The most prevalent approach for learning is the empirical risk minimizer (ERM), which adapts the model's weights to reduce the loss on a training set and…

Machine Learning · Computer Science 2024-12-11 Koby Bibas

Total Generalized Variation (TGV) has recently been introduced as penalty functional for modelling images with edges as well as smooth variations. It can be interpreted as a "sparse" penalization of optimal balancing from the first up to…

Numerical Analysis · Mathematics 2020-05-21 Kristian Bredies , Tuomo Valkonen

This paper advocates a new paradigm Personalized Empirical Risk Minimization (PERM) to facilitate learning from heterogeneous data sources without imposing stringent constraints on computational resources shared by participating devices. In…

Machine Learning · Computer Science 2023-10-30 Yuyang Deng , Mohammad Mahdi Kamani , Pouria Mahdavinia , Mehrdad Mahdavi

In a recent work (arXiv-DOI: 1804.08072v1) we introduced the Modified Augmented Lagrangian Method (MALM) for the efficient minimization of objective functions with large quadratic penalty terms. From MALM there results an optimality…

Numerical Analysis · Mathematics 2018-06-22 Martin Neuenhofen

We formulate a principle for classification with the knowledge of the marginal distribution over the data points (unlabeled data). The principle is cast in terms of Tikhonov style regularization where the regularization penalty articulates…

Machine Learning · Computer Science 2012-12-12 Adrian Corduneanu , Tommi S. Jaakkola

Empirical risk minimization is the main tool for prediction problems, but its extension to relational data remains unsolved. We solve this problem using recent ideas from graph sampling theory to (i) define an empirical risk for relational…

Machine Learning · Statistics 2019-02-25 Victor Veitch , Morgane Austern , Wenda Zhou , David M. Blei , Peter Orbanz

We address a problem of covariance selection, where we seek a trade-off between a high likelihood against the number of non-zero elements in the inverse covariance matrix. We solve a maximum likelihood problem with a penalty term given by…

Computational Engineering, Finance, and Science · Computer Science 2007-05-23 Onureena Banerjee , Alexandre d'Aspremont , Laurent El Ghaoui

Modern multivariate machine learning and statistical methodologies estimate parameters of interest while leveraging prior knowledge of the association between outcome variables. The methods that do allow for estimation of relationships do…

Methodology · Statistics 2021-06-10 Ben Sherwood , Bradley S. Price

In randomized controlled trials, adjusting for baseline covariates is often applied to improve the precision of treatment effect estimation. However, missingness in covariates is common. Recently, Zhao & Ding (2022) studied two simple…

Methodology · Statistics 2024-08-28 Yilin Song , James P. Hughes , Ting Ye

We introduce a general framework for estimation of inverse covariance, or precision, matrices from heterogeneous populations. The proposed framework uses a Laplacian shrinkage penalty to encourage similarity among estimates from disparate,…

Machine Learning · Statistics 2016-01-05 Takumi Saegusa , Ali Shojaie

It has become increasingly common nowadays to collect observations of feature and response pairs from different environments. As a consequence, one has to apply learned predictors to data with a different distribution due to distribution…

Methodology · Statistics 2023-10-31 Kang Du , Yu Xiang