paper-with-me

홈 › Papers

Formal Limitations on the Measurement of Mutual Information

2018-11-10 · ICLR 2019 5 · David McAllester, Karl Stratos

Measuring mutual information from finite data is difficult. Recent work has considered variational methods maximizing a lower bound. In this paper, we prove that serious statistical limitations are inherent to any method of measuring mutual information. More specifically, we show that any distribution-free high-confidence lower bound on mutual information estimated from N samples cannot be larger than O(ln N ).

📄 PDF Abstract BibTeX arXiv:1811.04251

Code (2)

karlstratos/doe 공식 구현 pytorch
createamind/keras-cpcgan tf

Similar Papers 제목 키워드 기반

Mutual Wasserstein Discrepancy Minimization for Sequential Recommendation

2023-01-28 · Ziwei Fan, Zhiwei Liu, Hao Peng, Philip S Yu

Self-supervised sequential recommendation significantly improves recommendation performance by maximizing mutual information with well-designed data augmentations. However, the mutual information estimation is based on t…

Contrastive LearningMutual Information EstimationSelf-Supervised LearningSequential Recommendation

Information-Theoretic Optimization for Task-Adapted Compressed Sensing Magnetic Resonance Imaging

2026-04-14 · Xinyu Peng, Ziyang Zheng, Wenrui Dai, Duoduo Xue 외 arxiv

Task-adapted compressed sensing magnetic resonance imaging (CS-MRI) is emerging to address the specific demands of downstream clinical tasks with significantly fewer k-space measurements than required by Nyquist sampling…

Medical Diagnosis

Which Mutual-Information Representation Learning Objectives are Sufficient for Control?

2021-06-14 · NeurIPS 2021 12 · Kate Rakelly, Abhishek Gupta, Carlos Florensa, Sergey Levine

Mutual information maximization provides an appealing formalism for learning representations of data. In the context of reinforcement learning (RL), such representations can accelerate learning by discarding irrelevant a…

Reinforcement Learning (RL)Representation Learning

Approximate Computational Approaches for Bayesian Sensor Placement in High Dimensions

2017-03-01 · Xiao Lin, Asif Chowdhury, Xiaofan Wang, Gabriel Terejanu

Since the cost of installing and maintaining sensors is usually high, sensor locations are always strategically selected. For those aiming at inferring certain quantities of interest (QoI), it is desirable to explore the…

Bayesian OptimizationVocal Bursts Intensity Prediction

Designed Measurements for Vector Count Data

2013-12-01 · NeurIPS 2013 12 · Liming Wang, David E. Carlson, Miguel Rodrigues, David Wilcox 외

We consider design of linear projection measurements for a vector Poisson signal model. The projections are performed on the vector Poisson rate, $X\in\mathbb{R}_+^n$, and the observed data are a vector of counts, $Y\in\…

Compressive Sensing