Publications

Conservation Laws for Diffusion Models

Ziv Aharoni and Henry D. Pfister

arXiv:2607.10067. arXiv Project Code

Neural Polar Decoders for Receivers in Wireless Communication

Rom Hirsch, Ziv Aharoni, Henry D. Pfister, and Haim H. Permuter

IEEE Transactions on Communications, 74, 6889–6903. DOI

Optimized Polar Codes via Mutual Information Maximization with Neural Polar Decoders

Ziv Aharoni, Bashar Huleihel, Henry D. Pfister, and Haim H. Permuter

IEEE Transactions on Communications, 74, 5820–5832. DOI Code

Neural Polar Decoders for DNA Data Storage

Ziv Aharoni and Henry D. Pfister

IEEE Journal on Selected Areas in Information Theory, 6, 403–416. DOI Code

The Duality Upper Bound for Finite-State Channels with Feedback

Bashar Huleihel, Oron Sabag, Ziv Aharoni, and Haim H. Permuter

IEEE Transactions on Information Theory, 71(5), 3255–3270. DOI

Data-Driven Neural Polar Decoders for Unknown Channels with and without Memory

Ziv Aharoni, Bashar Huleihel, Henry D. Pfister, and Haim H. Permuter

IEEE Transactions on Information Theory, 70(12), 8495–8510. DOI arXiv Code

Data-Driven Optimization of Directed Information over Discrete Alphabets

Dor Tsur, Ziv Aharoni, Ziv Goldfeld, and Haim H. Permuter

IEEE Transactions on Information Theory, 70(3), 1652–1670. DOI

Neural Estimation and Optimization of Directed Information over Continuous Spaces

Dor Tsur, Ziv Aharoni, Ziv Goldfeld, and Haim H. Permuter

IEEE Transactions on Information Theory, 69(8), 4777–4798. DOI arXiv

Feedback Capacity of Ising Channels with Large Alphabet via Reinforcement Learning

Ziv Aharoni, Oron Sabag, and Haim H. Permuter

IEEE Transactions on Information Theory, 68(9), 5637–5656. DOI arXiv

Capacity Estimation Using Machine Learning

Ziv Aharoni, Dor Tsur, Ziv Goldfeld, and Haim H. Permuter

In Machine Learning and Wireless Communications, Cambridge University Press, pp. 317–350. DOI

A Study of Neural Polar Decoders for Communication

Rom Hirsch, Ziv Aharoni, Henry D. Pfister, and Haim H. Permuter

NeurIPS 2025 Workshop on AI and ML for Next-Generation Wireless Communications and Networking (AI4NextG). arXiv NeurIPS

Neural Polar Decoders for Deletion Channels

Ziv Aharoni and Henry D. Pfister

IEEE International Symposium on Information Theory (ISIT), pp. 1–6. DOI

Neural Estimation of Multi-User Capacity Regions over Discrete Channels

Bashar Huleihel, Dor Tsur, Ziv Aharoni, Oron Sabag, and Haim H. Permuter

ISIT, pp. 1191–1196. DOI

Code Rate Optimization via Neural Polar Decoders

Ziv Aharoni, Bashar Huleihel, Henry D. Pfister, and Haim H. Permuter

ISIT, pp. 2424–2429. DOI

Data-Driven List Polar Decoder for Symmetric and Asymmetric Input Distributions

Ziv Aharoni, Bashar Huleihel, Henry D. Pfister, and Haim H. Permuter

International Zurich Seminar on Information and Communication (IZS), pp. 77–81. DOI

Neural Estimation of Multi-User Capacity Regions

Bashar Huleihel, Dor Tsur, Ziv Aharoni, Oron Sabag, and Haim H. Permuter

ISIT, pp. 2380–2385. DOI

Data-Driven Polar Codes for Unknown Channels with and without Memory

Ziv Aharoni, Bashar Huleihel, Henry D. Pfister, and Haim H. Permuter

ISIT, pp. 1890–1895. DOI

Density Estimation of Processes with Memory via Donsker Vardhan

Ziv Aharoni, Dor Tsur, and Haim H. Permuter

ISIT, pp. 330–335. DOI

Optimizing Estimated Directed Information over Discrete Alphabets

Dor Tsur, Ziv Aharoni, Ziv Goldfeld, and Haim H. Permuter

ISIT, pp. 2898–2903. DOI

Capacity of Continuous Channels with Memory via Directed Information Neural Estimator

Ziv Aharoni, Dor Tsur, Ziv Goldfeld, and Haim H. Permuter

ISIT, pp. 2014–2019. DOI

Reinforcement Learning Technique for Finding the Feedback Capacity

Ziv Aharoni, Oron Sabag, and Haim H. Permuter

IZS, p. 95, invited. DOI

Computing the Feedback Capacity of Finite State Channels Using Reinforcement Learning

Ziv Aharoni, Oron Sabag, and Haim H. Permuter

ISIT, pp. 837–841. Jack Keil Wolf Best Paper Award finalist. DOI

Brief Announcement: Gradual Learning of Deep Recurrent Neural Network

Ziv Aharoni, Gal Rattner, and Haim H. Permuter

CSCML, LNCS 10879, pp. 274–277. DOI