English
Related papers

Related papers: Optimal Empirical Risk Minimization under Temporal…

200 papers

Many machine learning tasks involve subpopulation shift where the testing data distribution is a subpopulation of the training distribution. For such settings, a line of recent work has proposed the use of a variant of empirical risk…

Machine Learning · Computer Science 2021-06-14 Runtian Zhai , Chen Dan , J. Zico Kolter , Pradeep Ravikumar

In machine learning applications, distribution shifts between training and target environments can lead to significant drops in model performance. This study investigates the impact of such shifts on binary classification models within the…

Machine Learning · Statistics 2024-08-20 Minji Kim , Seong Jin Lee , Bumsik Kim

A dynamical model consists of a continuous self-map $T: \mathcal{X} \to \mathcal{X}$ of a compact state space $\mathcal{X}$ and a continuous observation function $f: \mathcal{X} \to \mathbb{R}$. This paper considers the fitting of a…

Statistics Theory · Mathematics 2018-01-24 Kevin McGoff , Andrew B. Nobel

In this paper, we propose the first fully push-forward-based distributional reinforcement learning algorithm, named PACER, which consists of a distributional critic, a stochastic actor and a sample-based encourager. Specifically, the…

Machine Learning · Computer Science 2024-10-10 Wensong Bai , Chao Zhang , Yichao Fu , Peilin Zhao , Hui Qian , Bin Dai

We propose a new stochastic optimization framework for empirical risk minimization problems such as those that arise in machine learning. The traditional approaches, such as (mini-batch) stochastic gradient descent (SGD), utilize an…

Machine Learning · Statistics 2020-02-04 Kenji Kawaguchi , Haihao Lu

Recent development in the data-driven decision science has seen great advances in individualized decision making. Given data with individual covariates, treatment assignments and outcomes, policy makers best individualized treatment rule…

Machine Learning · Statistics 2020-06-29 Weibin Mo , Zhengling Qi , Yufeng Liu

We introduce a distributionally robust approach that enhances the reliability of offline policy evaluation in contextual bandits under general covariate shifts. Our method aims to deliver robust policy evaluation results in the presence of…

Machine Learning · Computer Science 2024-08-12 Yihong Guo , Hao Liu , Yisong Yue , Anqi Liu

Deep learning models often struggle under natural distribution shifts, a common challenge in real-world deployments. Test-Time Adaptation (TTA) addresses this by adapting models during inference without labeled source data. We present the…

Computer Vision and Pattern Recognition · Computer Science 2026-03-23 John Turnbull , Shivam Grover , Amin Jalali , Ali Etemad

Distribution shifts between training and test data are inevitable over the lifecycle of a deployed model, leading to performance decay. Adapting a model on test samples can help mitigate this drop in performance. However, most test-time…

Machine Learning · Computer Science 2025-11-18 Mona Schirmer , Dan Zhang , Eric Nalisnick

Robustness to distributional shift is one of the key challenges of contemporary machine learning. Attaining such robustness is the goal of distributionally robust optimization, which seeks a solution to an optimization problem that is…

Machine Learning · Statistics 2020-03-24 Johannes Kirschner , Ilija Bogunovic , Stefanie Jegelka , Andreas Krause

Robotic systems must be able to quickly and robustly make decisions when operating in uncertain and dynamic environments. While Reinforcement Learning (RL) can be used to compute optimal policies with little prior knowledge about the…

Robotics · Computer Science 2016-09-13 Yunpeng Pan , Xinyan Yan , Evangelos Theodorou , Byron Boots

Standard deep reinforcement learning (DRL) aims to maximize expected reward, considering collected experiences equally in formulating a policy. This differs from human decision-making, where gains and losses are valued differently and…

Machine Learning · Computer Science 2023-11-17 Jared Markowitz , Ryan W. Gardner , Ashley Llorens , Raman Arora , I-Jeng Wang

In many estimation problems, e.g. linear and logistic regression, we wish to minimize an unknown objective given only unbiased samples of the objective function. Furthermore, we aim to achieve this using as few samples as possible. In the…

Machine Learning · Statistics 2015-02-26 Roy Frostig , Rong Ge , Sham M. Kakade , Aaron Sidford

We find economically and statistically significant gains when using machine learning for portfolio allocation between the market index and risk-free asset. Optimal portfolio rules for time-varying expected returns and volatility are…

Portfolio Management · Quantitative Finance 2021-11-05 Michael Pinelis , David Ruppert

Dynamic influence maximization problem (DIMP) aims to maintain a group of influential users within an evolving social network, so that the influence scope can be maximized at any given moment. A primary category of DIMP algorithms focuses…

Social and Information Networks · Computer Science 2023-11-28 Shaofeng Zhang , Shengcai Liu , Ke Tang

A key problem in the theory of meta-learning is to understand how the task distributions influence transfer risk, the expected error of a meta-learner on a new task drawn from the unknown task distribution. In this paper, focusing on fixed…

Machine Learning · Statistics 2021-06-15 Mikhail Konobeev , Ilja Kuzborskij , Csaba Szepesvári

Dynamic treatment regimens (DTRs) aim at tailoring individualized sequential treatment rules that maximize cumulative beneficial outcomes by accommodating patients' heterogeneity in decision-making. For many chronic diseases including type…

Methodology · Statistics 2024-04-23 Mochuan Liu , Yuanjia Wang , Haoda Fu , Donglin Zeng

Wasserstein distributionally robust optimization (WDRO) attempts to learn a model that minimizes the local worst-case risk in the vicinity of the empirical data distribution defined by Wasserstein ball. While WDRO has received attention as…

Machine Learning · Statistics 2020-06-23 Yongchan Kwon , Wonyoung Kim , Joong-Ho Won , Myunghee Cho Paik

We introduce a distributional method for learning the optimal policy in risk averse Markov decision process with finite state action spaces, latent costs, and stationary dynamics. We assume sequential observations of states, actions, and…

Machine Learning · Computer Science 2023-03-01 Ziteng Cheng , Sebastian Jaimungal , Nick Martin

We address the problem of inverse reinforcement learning in Markov decision processes where the agent is risk-sensitive. In particular, we model risk-sensitivity in a reinforcement learning framework by making use of models of human…

Machine Learning · Computer Science 2017-11-23 Lillian J. Ratliff , Eric Mazumdar