About

I'm a Senior Lecturer (Assistant Professor) in the School of Computer Science at Reichman University. I received my PhD in Electrical Engineering from Stanford University in 2017, advised by Andrea Goldsmith. From 2017 to 2021, I was a postdoctoral scholar and lecturer in the Department of Statistics at Stanford, advised by David Donoho.

My research lies at the intersection of mathematical statistics, information theory, and signal processing. I focus on understanding and developing methods for analyzing high-dimensional, sparse, and noisy data — including time-series and text. My work blends rigorous mathematical theory with ambitious computational experiments and data analysis.

I'm always on the lookout for motivated graduate students with a strong mathematical background and a passion for data science. If that sounds like you, take a look at my current list of open projects.

Address

C.121b
Efi Arazi School of Computer Science
Reichman University (formerly IDC)
Herzliya, Israel

Email

alon.kipnis@runi.ac.il
kipnisal@alumni.stanford.edu

Journal publications under review

• Tingnan Gong, Alon Kipnis, and Yao Xie. (2026). Higher-criticism for sparse multi-stream change-point detection

Journal Publications

• Alon Kipnis. (2025). The minimax risk in testing uniformly over large alphabets under missing-ball alternatives. IEEE Transactions on Information Theory

• Alon Kipnis, Ben Galili, and Zohar Yakhini. (2025). Higher criticism for rare and weak non-proportional hazard deviations in survival analysis. Biometrika

• Shira Faigenbaum-Golovin, Alon Kipnis, Axel Bühler, Eli Piasetzky, Thomas Römer, and Israel Finkelstein. (2025) Critical biblical studies via word frequency analysis: unveiling text authorship. PLOS One

• Alon Kipnis. (2025). Unification of rare/weak detection models using moderate deviations analysis and log-chisquared P-values. Statistica Sinica

• Idan Kashtan and Alon Kipnis (2024). An information-theoretic approach for detecting edits in AI-generated text. Harvard Data Science Review

• David L. Donoho and Alon Kipnis. (2024). The impossibility region for detecting sparse mixtures using the higher criticism. Annals of Applied Probability

• Alon Kipnis and John C. Duchi. (2022). Mean estimation from one-bit measurements. IEEE Transactions on Information Theory

• David L. Donoho and Alon Kipnis. (2022). Higher Criticism to compare two large frequency tables, with sensitivity to possible rare and weak differences. Annals of Statistics

• Alon Kipnis. (2022). Higher criticism for discriminating word-frequency tables and testing authorship. Annals of Applied Statistics

• Alon Kipnis and Galen Reeves. (2021). Gaussian approximation of quantization error for estimation from compressed data. IEEE Transactions on Information Theory

• Alon Kipnis, Stefano Rini, and Andrea J. Goldsmith. (2021). The rate-distortion risk in estimation from compressed data. IEEE Transactions on Information Theory

• Stefano Rini, Alon Kipnis, Ruiyang Song, and Andrea J. Goldsmith. (2019). The compress-and-estimate coding scheme for Gaussian sources. IEEE Transactions on Wireless Communications

• Alon Kipnis, Andrea J. Goldsmith and Yonina C. Eldar. (2018). The distortion rate function of sampled Wiener Processes. IEEE Transactions on Information Theory

• Alon Kipnis, Andrea J. Goldsmith, and Yonina, C. Eldar. (2018). Fundamental distortion limits of analog to digital compression. IEEE Transactions on Information Theory

• Alon Kipnis, Yonina C. Eldar, and Andrea J. Goldsmith. (2018). Analog-to-digital compression: a new paradigm for converting signals to bits. IEEE Signal Processing Magazine

• Alon Kipnis, Andrea J. Goldsmith and Yonina, C. Eldar. (2017). The distortion rate function of cyclostationary Gaussian processes. IEEE Transactions on Information Theory

• Alon Kipnis, Andrea J. Goldsmith, Yonina, C. Eldar and Tsachy Weissman. (2016). Distortion rate function of sub-Nyquist sampled Gaussian sources. IEEE Transactions on Information Theory

• Daniel Alpay and Alon Kipnis. (2015). Wiener chaos approach to optimal prediction. Numerical Functional Analysis and Optimization

• Daniel Alpay and Alon Kipnis. (2013). A generalized white noise space approach to stochastic integration for a class of Gaussian stationary increment processes. Opuscula Mathematica

Book Chapters

• Alon Kipnis, Yonina C. Eldar and Andrea J. Goldsmith. (2021). An information-theoretic approach to analog-to-digital compression

Refereed Conference Publications

• Alon Kipnis. Calibrating the Calibration Tester: Optimal Binning and Minimax Calibration Testing for Continuous Predictive Models. 2026, Workshop Calibration for Modern AI. Best non-student paper award.

• Adam Vinestock and Alon Kipnis. Optimal Log-Likelihood Tests for Distinguishing Generative Models under Relative Entropy Constraints. Accepted to ISIT 2026.

• Alexander Tsvetkov and Alon Kipnis. Information parity: Measuring and predicting the multilingual capabilities of language models. Findings of the Association for Computational Linguistics (EMNLP) 2024

• Alexander Tsvetkov and Alon Kipnis. Multilingual compression parity: How efficiently large language models represent information across languages? ICML 2024 Workshop on Theoretical Foundations of Foundation Models

• Dana Levin and Alon Kipnis. The likelihood gain of a language model as a metric for text summarization. IEEE International Symposium on Information Theory 2024.

• Alon Kipnis. The minimax risk in testing the histogram of discrete distributions for uniformity under missing ball alternatives. 59th Annual Allerton Conference on Communication, Control, and Computing 2023

• Alexander Tsvetkov and Alon Kipnis. EntropyRank: Unsupervised keyphrase extraction via side-information optimization for language model-based text compression ICML 2023 Workshop on Neural Compression: From Information Theory to Applications

• Alon Kipnis. Rare and weak detection models under moderate deviations analysis and log-chisquared p-values. IEEE International Symposium on Information Theory 2022

• Alon Kipnis and David L. Donoho. Two-sample testing of word-frequency tables under rare/weak Perturbations. IEEE International Symposium on Information Theory 2021

• Alon Kipnis. Higher criticism as an unsupervised authorship discriminator. Conference and Labs of the Evaluation Forum 2020

• Alon Kipnis and Galen Reeves. Gaussian approximation of quantization error for estimation from compressed data. IEEE International Symposium on Information Theory 2019

• Alon Kipnis, Galen Reeves, and Yonina C. Eldar. Single-letter formulas for quantized compressed sensing with Gaussian codebooks. IEEE International Symposium on Information Theory 2018

• Georgia Murray, Alon Kipnis, and Andrea J. Goldsmith. Lossy compression of decimated Gaussian random walks. 52nd Annual Conference on Information Sciences and Systems 2018

• Alon Kipnis and John C. Duchi. Mean estimation from adaptive one-bit measurements. 55th Annual Allerton Conference on Communication, Control, and Computing 2017

• Alon Kipnis, Galen Reeves, Yonina C. Eldar and Andrea J. Goldsmith. Compressed sensing under optimal quantization. IEEE International Symposium on Information Theory 2017

• Alon Kipnis, Stefano Rini, and Andrea J. Goldsmith. Coding theorems for the compress and estimate source coding problem. IEEE International Symposium on Information Theory 2017

• Ruyang Song, Stefano Rini, Alon Kipnis, and Andrea J. Goldsmith. Optimal rate-allocation in multiterminal compress-and-estimate source coding. IEEE Information Theory Workshop 2016

• Alon Kipnis, Andrea J. Goldsmith, and Yonina C. Eldar, Information rates of sampled Wiener processes. IEEE International Symposium on Information Theory 2016

• Alon Kipnis, Stefano Rini, and Andrea J. Goldsmith. Multiterminal compress-and-estimate source coding. IEEE International Symposium on Information Theory 2016

• Milind Rao, Alon Kipnis, Tara Javidi, Yonina C. Eldar and Andrea J. Goldsmith. System identification from partial samples: non-asymptotic analysis. IEEE 55th Conference on Decision and Control 2016

• Alon Kipnis, Andrea J. Goldsmith and Yonina C. Eldar. Optimal trade-off between sampling rate and quantization precision in A/D conversion. 53rd Annual Allerton Conference on Communication, Control, and Computing 2015

• Alon Kipnis, Stefano Rini, and Andrea J. Goldsmith. The indirect rate-distortion function of a binary i.i.d source. IEEE Information Theory Workshop 2015

• Mainak Chowdhury, Alon Kipnis, and Andrea J. Goldsmith. Reliable uncoded communication in the quantized SIMO MAC. IEEE International Symposium on Information Theory 2015

• Alon Kipnis, Andreea J. Goldsmith, and Yonina C. Eldar. Optimal trade-off between sampling rate and quantization precision in Sigma-Delta A/D conversion. International Conference on Sampling Theory and Applications 2015

• Alon Kipnis, Andrea J. Goldsmith, and Yonina C. Eldar. Sub-Nyquist sampling achieves optimal rate-distortion. IEEE Information Theory Workshop 2015

• Alon Kipnis, Andrea J. Goldsmith, and Yonina C. Eldar. Rate-distortion function under sub-Nyquist nonuniform sampling. 52nd Annual Allerton Conference on Communication, Control, and Computing 2014

• Alon Kipnis, Andrea J. Goldsmith, and Yonina C. Eldar. Rate-distortion function of Gaussian Cyclostationary processes. IEEE International Symposium on Information Theory 2014

• Alon Kipnis, Andrea J. Goldsmith, Tsachy Weissman and Yonina C. Eldar. Rate-distortion function of sub-Nyquist sampled Gaussian processes corrupted by noise. 51st Annual Allerton Conference on Communication, Control, and Computing 2013

Dissertations

• Alon Kipnis. (2017). Fundamental performance limits of analog-to-digital compression

• Alon Kipnis. (2012). Generalized white noise space analysis and stochastic integration with respect to a class of Gaussian stationary increment processes

Patents

See here.

Current (Fall 2025/2026)

• Introduction to Information Theory (CS 3798)

• Applied AI and Data Science Studio (CS 3801)

Past

• Spring 2024/5:

• Machine Learning from Data (CS 3141)

• Seminar in Large Language Models and Information Theory (CS 3968)

• Fall 2024/5:

  • Advanced statistical analysis and model-based learning (formerly ‘Advanced Statistics for Data Science’) (CS 3676)

• Spring 2023/4:

  • Machine Learning from Data (CS 3141)

  • Seminar in Large Language Models and Information Theory (CS 3968)

• Fall 2023/4:

  • Introduction to Information Theory (CS 3798)

• Spring 2022/3:

  • Machine Learning from Data (CS 3141)

  • Advanced statistics for data science (CS 3676)

• Fall 2022/3:

  • Information-theoretical analysis of neural language models (CS 3890)

• Spring 2021/2:

  • Advanced statistics for data science (CS 3676)

Spring 2021/2: (Stanford STATS 285) Massive computational experiments, painlessly

• with David Donoho and Masha Lotfi

Fall 2020/1: (Stanford STATS 207) Introduction to time-series analysis (Fall 2020-2021)

• Multi-channel time-series prediction

• Goodness-of-fit and homogeneity testing with sparse data

• Text clustering, retrieval, and topic modeling

• Survival analysis

• Change-point detection

• Information-theoretic limitations of large language models