Search Results for author: Alon Kipnis

Found 7 papers, 1 papers with code

EntropyRank: Unsupervised Keyphrase Extraction via Side-Information Optimization for Language Model-based Text Compression

no code implementations25 Aug 2023 Alexander Tsvetkov, Alon Kipnis

We propose an unsupervised method to extract keywords and keyphrases from texts based on a pre-trained language model (LM) and Shannon's information maximization.

Keyphrase Extraction Language Modelling +1

Separating the Human Touch from AI-Generated Text using Higher Criticism: An Information-Theoretic Approach

no code implementations24 Aug 2023 Alon Kipnis

We propose a method to determine whether a given article was entirely written by a generative language model versus an alternative situation in which the article includes some significant edits by a different author, possibly a human.

Language Modelling

The Minimax Risk in Testing Uniformity of Poisson Data under Missing Ball Alternatives within a Hypercube

no code implementations29 May 2023 Alon Kipnis

When the expected number of samples $n$ and number of categories $N$ go to infinity while $\epsilon$ is small, the minimax risk asymptotes to $2\Phi(-n N^{2-2/p} \epsilon^2/\sqrt{8N})$; $\Phi(x)$ is the normal CDF.

Gaussian Approximation of Quantization Error for Estimation from Compressed Data

no code implementations9 Jan 2020 Alon Kipnis, Galen Reeves

We show that the Wasserstein distance between a bitrate-$R$ compressed version of $X$ and its observation under an AWGN-channel of signal-to-noise ratio $2^{2R}-1$ is sub-linear in the problem dimension.

Quantization

Higher Criticism for Discriminating Word-Frequency Tables and Testing Authorship

2 code implementations30 Oct 2019 Alon Kipnis

We apply this measure to authorship attribution challenges, where the goal is to identify the author of a document using other documents whose authorship is known.

Authorship Attribution

Mean Estimation from One-Bit Measurements

no code implementations10 Jan 2019 Alon Kipnis, John C. Duchi

We consider the problem of estimating the mean of a symmetric log-concave distribution under the constraint that only a single bit per sample from this distribution is available to the estimator.

Quantization

Mean Estimation from Adaptive One-bit Measurements

no code implementations2 Aug 2017 Alon Kipnis, John C. Duchi

We study the squared error risk in this estimation as a function of the number of samples and one-bit measurements $n$.

Statistics Theory Statistics Theory

Cannot find the paper you are looking for? You can Submit a new open access paper.