paper-with-me

홈 › Papers

ShakyPrepend: A Multi-Group Learner with Improved Sample Complexity

2026-03-07 · Lujing Zhang, Daniel Hsu, Sivaraman Balakrishnan arxiv

Multi-group learning is a learning task that focuses on controlling predictors' conditional losses over specified subgroups. We propose ShakyPrepend, a method that leverages tools inspired by differential privacy to obtain improved theoretical guarantees over existing approaches. Through numerical experiments, we demonstrate that ShakyPrepend adapts to both group structure and spatial heterogeneity. We provide practical guidance for deploying multi-group learning algorithms in real-world settings.

📄 PDF Abstract BibTeX arXiv:2603.07319

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

The price of multi-group transductive learning

2026-06-03 · Noah Bergam, Samuel Deng, Daniel Hsu arxiv

We show every multi-group learner in the transductive setting may incur a multiplicative penalty in its error rate on some group relative to the error rate achievable in the single-group setting, and the penalty can incr…

Context-lumpable stochastic bandits

2023-06-22 · NeurIPS 2023 11

We consider a contextual bandit problem with $S$ contexts and $K$ actions. In each round $t=1,2,\dots$, the learner observes a random context and chooses an action based on its past experience. The learner then observes …

Few-shot Learning with Global Relatedness Decoupled-Distillation

2021-07-12 · Yuan Zhou, Yanrong Guo, Shijie Hao, Richang Hong 외

Despite the success that metric learning based approaches have achieved in few-shot learning, recent works reveal the ineffectiveness of their episodic training mode. In this paper, we point out two potential reasons for…

Few-Shot LearningMetric Learning

Cost-Aware Learning for Improved Identifiability with Multiple Experiments

2018-02-12 · Longyun Guo, Jean Honorio, John Morgan

We analyze the sample complexity of learning from multiple experiments where the experimenter has a total budget for obtaining samples. In this problem, the learner should choose a hypothesis that performs well with resp…

Small-Group Learning, with Application to Neural Architecture Search

2020-12-23 · Xuefeng Du, Pengtao Xie

In human learning, an effective learning methodology is small-group learning: a small group of students work together towards the same learning objective, where they express their understanding of a topic to their peers,…

Neural Architecture Search