Alon Kipnis

Profile picture

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.

Contact

Office Hours (Spring 2024/2025)

Tuesdays, 14:00-15:00

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


Publications

Journal publications under review

Journal Publications

Book Chapters

Refereed Conference Publications

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

  • Alon Kipnis and Galen Reeves. Single-letter formulas for quantized compressed sensing with Gaussian codebooks. 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. emph{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. 52st 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

Patents

See this page, or search it yourself at SenseIP https://www.senseip.ai/.

Teaching

Office hours: Tuesdays. 14:00-15:00 Location: C.121b

Current (Spring 2024/5)

Past

  • 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 Lofti

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

Lecture 1 course outline, examples of time series data, models for time series data
Lecture 2 sample autocorrelation and basic theoretical constructs
Lecture 3 time series regression
Lecture 4 trend models and Data Wrangling
Lecture 5-6 ARMA/ARIMA Modeling I
Lecture 7 ARMA/ARIMA Modeling II
Lecture 8 ARIMA/SARIMA
Lecture 9 regression with autocorrelated errors and lagged regression
Lecture 10 efficient markets hypothesis and GARCH (guest lecture by David Donoho)
Lecture 11 spectral Analysis I
Lecture 12 spectral Analysis II
Lecture 13 spectral regression and principal components
Lecture 14 state-space modeling and the Kalman Filter
Lecture 15 estimation of state-space models
Lecture 16 dynamic linear models with switching
Lecture 17 stochastic volatility, Bayesian analysis of state-space models
Lecture 18 bootstrap reality check and technical trading rules (guest lecture by David Donoho)
Lecture 19 prophet (guest lecture by Sean Taylor)
Lecture 20 high-dimensional data, DeepAR, VEST


Available Research Projects

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

  • Information-theoretic limitations of large language models

  • Multi-channel time-series prediction

  • Test clustering, retreival, and topic modeling

  • Survival analysis

  • Change-point detection