paper-with-me

홈 › Papers

Estimating the Fundamental Limits is Easier than Achieving the Fundamental Limits

2017-07-05 · Jiantao Jiao, Yanjun Han, Irena Fischer-Hwang, Tsachy Weissman

We show through case studies that it is easier to estimate the fundamental limits of data processing than to construct explicit algorithms to achieve those limits. Focusing on binary classification, data compression, and prediction under logarithmic loss, we show that in the finite space setting, when it is possible to construct an estimator of the limits with vanishing error with $n$ samples, it may require at least $n\ln n$ samples to construct an explicit algorithm to achieve the limits.

📄 PDF Abstract BibTeX arXiv:1707.01203

Code (0)

등록된 구현이 없습니다.

Tasks

Binary ClassificationData CompressionGeneral Classification

Similar Papers 제목 키워드 기반

Limits of Approximating the Median Treatment Effect

2024-03-15 · Raghavendra Addanki, Siddharth Bhandari

Average Treatment Effect (ATE) estimation is a well-studied problem in causal inference. However, it does not necessarily capture the heterogeneity in the data, and several approaches have been proposed to tackle the iss…

Causal Inference

Towards Fundamental Limits of Multi-armed Bandits with Random Walk Feedback

2020-11-03 · Tianyu Wang, Lin F. Yang, Zizhuo Wang

In this paper, we consider a new Multi-Armed Bandit (MAB) problem where arms are nodes in an unknown and possibly changing graph, and the agent (i) initiates random walks over the graph by pulling arms, (ii) observes the…

Multi-Armed BanditsRecommendation Systems

Limits of Estimating Heterogeneous Treatment Effects: Guidelines for Practical Algorithm Design

2018-07-01 · ICML 2018 7 · Ahmed Alaa, Mihaela Schaar

Estimating heterogeneous treatment effects from observational data is a central problem in many domains. Because counterfactual data is inaccessible, the problem differs fundamentally from supervised learning, and e…

counterfactualGaussian ProcessesSelection bias

Estimating Certain Integral Probability Metric (IPM) is as Hard as Estimating under the IPM

2019-11-02 · Tengyuan Liang

We study the minimax optimal rates for estimating a range of Integral Probability Metrics (IPMs) between two unknown probability measures, based on $n$ independent samples from them. Curiously, we show that estimating th…

Improving Pairwise Ranking for Multi-label Image Classification

2017-04-11 · CVPR 2017 7 · Yuncheng Li, Yale Song, Jiebo Luo

Learning to rank has recently emerged as an attractive technique to train deep convolutional neural networks for various computer vision tasks. Pairwise ranking, in particular, has been successful in multi-label image cl…

ClassificationGeneral Classificationimage-classificationImage Classification+2