paper-with-me

홈 › Papers

Incorporating Unlabeled Data into Distributionally Robust Learning

2019-12-16 · Charlie Frogner, Sebastian Claici, Edward Chien, Justin Solomon

We study a robust alternative to empirical risk minimization called distributionally robust learning (DRL), in which one learns to perform against an adversary who can choose the data distribution from a specified set of distributions. We illustrate a problem with current DRL formulations, which rely on an overly broad definition of allowed distributions for the adversary, leading to learned classifiers that are unable to predict with any confidence. We propose a solution that incorporates unlabeled data into the DRL problem to further constrain the adversary. We show that this new formulation is tractable for stochastic gradient-based optimization and yields a computable guarantee on the future performance of the learned classifier, analogous to -- but tighter than -- guarantees from conventional DRL. We examine the performance of this new formulation on 14 real datasets and find that it often yields effective classifiers with nontrivial performance guarantees in situations where conventional DRL produces neither. Inspired by these results, we extend our DRL formulation to active learning with a novel, distributionally-robust version of the standard model-change heuristic. Our active learning algorithm often achieves superior learning performance to the original heuristic on real datasets.

📄 PDF Abstract BibTeX arXiv:1912.07729

Code (0)

등록된 구현이 없습니다.

Tasks

Active Learning

Similar Papers 제목 키워드 기반

Out-Of-Domain Unlabeled Data Improves Generalization

2023-09-29 · Amir Hossein Saberi, Amir Najafi, Alireza Heidari, Mohammad Hosein Movasaghinia 외

We propose a novel framework for incorporating unlabeled data into semi-supervised classification problems, where scenarios involving the minimization of either i) adversarially robust or ii) non-robust loss functions ha…

Fast Bellman Updates for Wasserstein Distributionally Robust MDPs

2023-09-21 · NeurIPS 2023 11

Markov decision processes (MDPs) often suffer from the sensitivity issue under model ambiguity. In recent years, robust MDPs have emerged as an effective framework to overcome this challenge. Distributionally robust MDPs…

Distributionally Robust Data Join

2022-02-11 · Pranjal Awasthi, Christopher Jung, Jamie Morgenstern

Suppose we are given two datasets: a labeled dataset and unlabeled dataset which also has additional auxiliary features not present in the first dataset. What is the most principled way to use these datasets together to …

Distributionally Robust Semi-Supervised Learning for People-Centric Sensing

2018-11-12 · Kaixuan Chen, Lina Yao, Dalin Zhang, Xiaojun Chang 외

Semi-supervised learning is crucial for alleviating labelling burdens in people-centric sensing. However, human-generated data inherently suffer from distribution shift in semi-supervised learning due to the diverse biol…

Activity RecognitionGesture RecognitionIntent DetectionMuscular Movement Recognition

Distributionally Robust Classification for Multi-source Unsupervised Domain Adaptation

2026-01-29 · Seonghwi Kim, Sung Ho Jo, Wooseok Ha, Minwoo Chae arxiv

Unsupervised domain adaptation (UDA) is a statistical learning problem when the distribution of training (source) data is different from that of test (target) data. In this setting, one has access to labeled data only fr…

Unsupervised Domain Adaptation