5 citations · 8 across the 13 of their papers we have counts for
13 papers
Conservation Laws for Diffusion Models
Ziv Aharoni, Henry D. Pfister
While autoregressive models optimize the exact data likelihood via the chain rule, diffusion models are typically trained with denoising objectives. We develop conservation laws ba…
A Study of Neural Polar Decoders for Communication
Rom Hirsch, Ziv Aharoni, Henry D. Pfister +1
In this paper, we adapt and analyze Neural Polar Decoders (NPDs) for end-to-end communication systems. While prior work demonstrated the effectiveness of NPDs on synthetic channels…
Neural Polar Decoders for Deletion Channels
Ziv Aharoni, Henry D. Pfister
This paper introduces a neural polar decoder (NPD) for deletion channels with a constant deletion rate. Existing polar decoders for deletion channels exhibit high computational com…
Neural Polar Decoders for DNA Data Storage
Ziv Aharoni, Henry D. Pfister
Synchronization errors, such as insertions and deletions, present a fundamental challenge in DNA-based data storage systems, arising from both synthesis and sequencing noise. These…
Code Rate Optimization via Neural Polar Decoders
Ziv Aharoni, Bashar Huleihel, Henry D Pfister +1
This paper proposes a method to optimize communication code rates via the application of neural polar decoders (NPDs). Employing this approach enables simultaneous optimization of…
The Duality Upper Bound for Finite-State Channels with Feedback
Bashar Huleihel, Oron Sabag, Ziv Aharoni +1
This paper investigates the capacity of finite-state channels (FSCs) with feedback. We derive an upper bound on the feedback capacity of FSCs by extending the duality upper bound m…
Data-Driven Neural Polar Codes for Unknown Channels With and Without Memory
Ziv Aharoni, Bashar Huleihel, Henry D. Pfister +1
In this work, a novel data-driven methodology for designing polar codes for channels with and without memory is proposed. The methodology is suitable for the case where the channel…
Data-Driven Optimization of Directed Information over Discrete Alphabets
Dor Tsur, Ziv Aharoni, Ziv Goldfeld +1
Directed information (DI) is a fundamental measure for the study and analysis of sequential stochastic models. In particular, when optimized over input distributions it characteriz…
Neural Estimation and Optimization of Directed Information over Continuous Spaces
Dor Tsur, Ziv Aharoni, Ziv Goldfeld +1
This work develops a new method for estimating and optimizing the directed information rate between two jointly stationary and ergodic stochastic processes. Building upon recent ad…
Reinforcement Learning Evaluation and Solution for the Feedback Capacity of the Ising Channel with Large Alphabet
Ziv Aharoni, Oron Sabag, Haim Henri Permuter
We propose a new method to compute the feedback capacity of unifilar finite state channels (FSCs) with memory using reinforcement learning (RL). The feedback capacity was previousl…
Capacity of Continuous Channels with Memory via Directed Information Neural Estimator
Ziv Aharoni, Dor Tsur, Ziv Goldfeld +1
Calculating the capacity (with or without feedback) of channels with memory and continuous alphabets is a challenging task. It requires optimizing the directed information (DI) rat…
Computing the Feedback Capacity of Finite State Channels using Reinforcement Learning
Ziv Aharoni, Oron Sabag, Haim Henry Permuter
In this paper, we propose a novel method to compute the feedback capacity of channels with memory using reinforcement learning (RL). In RL, one seeks to maximize cumulative rewards…
Gradual Learning of Recurrent Neural Networks
Ziv Aharoni, Gal Rattner, Haim Permuter
Recurrent Neural Networks (RNNs) achieve state-of-the-art results in many sequence-to-sequence modeling tasks. However, RNNs are difficult to train and tend to suffer from overfitt…