English
Related papers

Related papers: Out-of-Distribution Generalization via Risk Extrap…

200 papers

We consider the problem of function estimation in the case where the data distribution may shift between training and test time, and additional information about it may be available at test time. This relates to popular scenarios such as…

Machine Learning · Statistics 2013-06-05 Bernhard Schölkopf , Dominik Janzing , Jonas Peters , Kun Zhang

Extrapolation in reinforcement learning is the ability to generalize at test time given states that could never have occurred at training time. Here we consider four factors that lead to improved extrapolation in a simple Gridworld…

Machine Learning · Computer Science 2020-04-16 Eugene Charniak

Learning models that are robust to distribution shifts is a key concern in the context of their real-life applicability. Invariant Risk Minimization (IRM) is a popular framework that aims to learn robust models from multiple environments.…

Machine Learning · Computer Science 2023-04-04 Moulik Choraria , Ibtihal Ferwana , Ankur Mani , Lav R. Varshney

Modern deep learning techniques have illustrated their excellent capabilities in many areas, but relies on large training data. Optimization-based meta-learning train a model on a variety tasks, such that it can solve new learning tasks…

Machine Learning · Computer Science 2023-02-23 Penghao Jiang , Ke Xin , Zifeng Wang , Chunxi Li

Since out-of-distribution generalization is a generally ill-posed problem, various proxy targets (e.g., calibration, adversarial robustness, algorithmic corruptions, invariance across shifts) were studied across different research programs…

Research in machine learning is making progress in fixing its own reproducibility crisis. Reinforcement learning (RL), in particular, faces its own set of unique challenges. Comparison of point estimates, and plots that show successful…

Machine Learning · Computer Science 2024-02-07 Ted Fujimoto , Joshua Suetterlein , Samrat Chatterjee , Auroop Ganguly

Covariate distribution shifts and adversarial perturbations present robustness challenges to the conventional statistical learning framework: mild shifts in the test covariate distribution can significantly affect the performance of the…

Machine Learning · Statistics 2024-05-21 Tengyuan Liang

We study the regret guarantee for risk-sensitive reinforcement learning (RSRL) via distributional reinforcement learning (DRL) methods. In particular, we consider finite episodic Markov decision processes whose objective is the entropic…

Machine Learning · Computer Science 2024-01-26 Hao Liang , Zhi-Quan Luo

Enhancing the stability of machine learning algorithms under distributional shifts is at the heart of the Out-of-Distribution (OOD) Generalization problem. Derived from causal learning, recent works of invariant learning pursue strict…

Machine Learning · Computer Science 2024-02-15 Jiashuo Liu , Jiayun Wu , Jie Peng , Xiaoyu Wu , Yang Zheng , Bo Li , Peng Cui

Despite impressive success in many tasks, deep learning models are shown to rely on spurious features, which will catastrophically fail when generalized to out-of-distribution (OOD) data. Invariant Risk Minimization (IRM) is proposed to…

Machine Learning · Computer Science 2022-12-20 Shiji Xin , Yifei Wang , Jingtong Su , Yisen Wang

We consider the problem of predicting a response $Y$ from a set of covariates $X$ when test and training distributions differ. Since such differences may have causal explanations, we consider test distributions that emerge from…

Methodology · Statistics 2021-08-19 Rune Christiansen , Niklas Pfister , Martin Emil Jakobsen , Nicola Gnecco , Jonas Peters

Machine learning algorithms typically assume that the training and test samples come from the same distributions, i.e., in-distribution. However, in open-world scenarios, streaming big data can be Out-Of-Distribution (OOD), rendering these…

Machine Learning · Computer Science 2022-11-10 Anique Tahir , Lu Cheng , Ruocheng Guo , Huan Liu

We consider the problem of learning models for risk-sensitive reinforcement learning. We theoretically demonstrate that proper value equivalence, a method of learning models which can be used to plan optimally in the risk-neutral setting,…

Machine Learning · Computer Science 2023-12-05 Tyler Kastner , Murat A. Erdogdu , Amir-massoud Farahmand

Reinforcement Learning (RL) algorithms for safety alignment of Large Language Models (LLMs), such as Direct Preference Optimization (DPO), encounter the challenge of distribution shift. Current approaches typically address this issue…

Computation and Language · Computer Science 2025-06-17 Qiyuan Deng , Xuefeng Bai , Kehai Chen , Yaowei Wang , Liqiang Nie , Min Zhang

Out-of-distribution (OOD) generalization is a complicated problem due to the idiosyncrasies of possible distribution shifts between training and test domains. Most benchmarks employ diverse datasets to address this issue; however, the…

Machine Learning · Computer Science 2023-12-18 Kaican Li , Yifan Zhang , Lanqing Hong , Zhenguo Li , Nevin L. Zhang

Offline reinforcement learning (RL) presents distinct challenges as it relies solely on observational data. A central concern in this context is ensuring the safety of the learned policy by quantifying uncertainties associated with various…

Machine Learning · Computer Science 2025-07-03 Xiaocong Chen , Siyu Wang , Tong Yu , Lina Yao

A pervasive phenomenon in machine learning applications is distribution shift, where training and deployment conditions for a machine learning model differ. As distribution shift typically results in a degradation in performance, much…

Machine Learning · Statistics 2024-01-23 Philip Amortila , Tongyi Cao , Akshay Krishnamurthy

Reinforcement Learning (RL) has made notable success in decision-making fields like autonomous driving and robotic manipulation. Yet, its reliance on real-time feedback poses challenges in costly or hazardous settings. Furthermore, RL's…

Machine Learning · Computer Science 2024-07-19 Minjae Cho , Chuangchuang Sun

Current machine learning models achieve super-human performance in many real-world applications. Still, they are susceptible against imperceptible adversarial perturbations. The most effective solution for this problem is adversarial…

Machine Learning · Computer Science 2023-01-26 Mohammad Azizmalayeri , Arman Zarei , Alireza Isavand , Mohammad Taghi Manzuri , Mohammad Hossein Rohban

Out-of-distribution (OOD) generalization remains a fundamental challenge in real-world classification, where test distributions often differ substantially from training data. Most existing approaches pursue domain-invariant representations,…

Machine Learning · Computer Science 2026-01-30 Chen Cheng , Ang Li