The price of multi-group transductive learning
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 increasing linearly with the number of groups, up to roughly the square-root of the sample size. This stands in stark contrast to optimal multi-group learners in an analogous (group-realizable) statistical setting, where the penalty is always at most logarithmic in the sample size and independent of the number of groups.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Universal Decompositional Semantic Parsing
We introduce a transductive model for parsing into Universal Decompositional Semantics (UDS) representations, which jointly learns to map natural language utterances into UDS graph structures and annotate the graph with …
AttributePredictionSemantic ParsingPrice-guided user attention in large-scale E-commerce group recommendation
Existing group recommender systems utilize attention mechanisms to identify critical users who influence group decisions the most. We analyzed user attention scores from a widely-used group recommendation model on a real…
Decision MakingRecommendation SystemsGroup-wise oracle-efficient algorithms for online multi-group learning
We study the problem of online multi-group learning, a learning model in which an online learner must simultaneously achieve small prediction regret on a large collection of (possibly overlapping) subsequences correspond…
FairnessGroup network effects in price competition
The partition of society into groups, polarization, and social networks are part of most conversations today. How do they influence price competition? We discuss Bertrand duopoly equilibria with demand subject to network…
On Label-Efficient Computer Vision: Building Fast and Effective Few-Shot Image Classifiers
Modern deep learning requires large-scale extensively labelled datasets for training. Few-shot learning aims to alleviate this issue by learning effectively from few labelled examples. In previously proposed few-shot vis…
Active LearningContinual LearningCross-Domain Few-ShotFew-Shot Learning+3