paper-with-me

홈 › Papers

On the Statistical Complexity of Sample Amplification

2022-01-12 · Brian Axelrod, Shivam Garg, Yanjun Han, Vatsal Sharan, Gregory Valiant

The ``sample amplification'' problem formalizes the following question: Given $n$ i.i.d. samples drawn from an unknown distribution $P$, when is it possible to produce a larger set of $n+m$ samples which cannot be distinguished from $n+m$ i.i.d. samples drawn from $P$? In this work, we provide a firm statistical foundation for this problem by deriving generally applicable amplification procedures, lower bound techniques and connections to existing statistical notions. Our techniques apply to a large class of distributions including the exponential family, and establish a rigorous connection between sample amplification and distribution learning.

📄 PDF Abstract BibTeX arXiv:2201.04315

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

GANplifying Event Samples

2020-08-14 · Anja Butter, Sascha Diefenbacher, Gregor Kasieczka, Benjamin Nachman 외

A critical question concerning generative networks applied to event generation in particle physics is if the generated events add statistical precision beyond the training sample. We show for a simple example with increa…

Data Amplification: A Unified and Competitive Approach to Property Estimation

2019-03-29 · NeurIPS 2018 12 · Yi Hao, Alon Orlitsky, Ananda T. Suresh, Yihong Wu

Estimating properties of discrete distributions is a fundamental problem in statistical learning. We design the first unified, linear-time, competitive, property estimator that for a wide class of properties and for all …

Forecasting Generative Amplification

2025-09-09 · Henning Bahl, Sascha Diefenbacher, Nina Elmer, Tilman Plehn 외 arxiv

Generative networks are perfect tools to enhance the speed and precision of LHC simulations. Especially when generating events beyond the size of the training dataset, it is important to understand their statistical prec…

Optimal Testing of Discrete Distributions with High Probability

2020-09-14 · Ilias Diakonikolas, Themis Gouleakis, Daniel M. Kane, John Peebles 외

We study the problem of testing discrete distributions with a focus on the high probability regime. Specifically, given samples from one or more discrete distributions, a property $\mathcal{P}$, and parameters $0< \epsil…

Vocal Bursts Intensity Prediction

Position: The Complexity of Perfect AI Alignment -- Formalizing the RLHF Trilemma

2025-11-23 · Subramanyam Sahoo, Aman Chadha, Vinija Jain, Divya Chaudhary arxiv

Reinforcement Learning from Human Feedback (RLHF) is widely used for aligning large language models, yet practitioners face a persistent puzzle: improving safety often reduces fairness, scaling to diverse populations bec…

Reinforcement Learning