# Deep Task-Based Analog-to-Digital Conversion

arXiv: https://arxiv.org/abs/2201.12634 · HTML: https://mlsanity.com/paper/2201.12634/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 50 references that are in the map.
- First posted on arXiv 29 Jan 2022.

## Builds on (most cited first, 21 of 21)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [A Tutorial on Bayesian Optimization](https://mlsanity.com/paper/1807.02811/) (2018)
- [Gradient-based Hyperparameter Optimization through Reversible Learning](https://mlsanity.com/paper/1502.03492/) (2015)
- [Soft-to-Hard Vector Quantization for End-to-End Learning Compressible Representations](https://mlsanity.com/paper/1704.00648/) (2017)
- [Learned Optimizers that Scale and Generalize](https://mlsanity.com/paper/1703.04813/) (2017)
- [BoTorch: A Framework for Efficient Monte-Carlo Bayesian Optimization](https://mlsanity.com/paper/1910.06403/) (2019)
- [DeepSIC: Deep Soft Interference Cancellation for Multiuser MIMO Detection](https://mlsanity.com/paper/2002.03214/) (2020)
- [Adaptive Ultrasound Beamforming using Deep Learning](https://mlsanity.com/paper/1909.10342/) (2019)
- [Neural Network Detection of Data Sequences in Communication Systems](https://mlsanity.com/paper/1802.02046/) (2018)
- [Deep Task-Based Quantization](https://mlsanity.com/paper/1908.06845/) (2019)
- [Dynamic Metasurface Antennas for 6G Extreme Massive MIMO Communications](https://mlsanity.com/paper/2006.07838/) (2020)
- [Learning Sub-Sampling and Signal Recovery with Applications in Ultrasound Imaging](https://mlsanity.com/paper/1908.05764/) (2019)
- [Asymptotic Task-Based Quantization with Application to Massive MIMO](https://mlsanity.com/paper/1811.10077/) (2018)
- [Task-Based Analog-to-Digital Converters](https://mlsanity.com/paper/2009.14088/) (2020)
- [RF Chain Reduction for MIMO Systems: A Hardware Prototype](https://mlsanity.com/paper/1905.05315/) (2019)
- [Learning to Sample: Data-Driven Sampling and Reconstruction of FRI Signals](https://mlsanity.com/paper/2106.14500/) (2021)
- [Analog-to-Digital Compression: A New Paradigm for Converting Signals to Bits](https://mlsanity.com/paper/1801.06718/) (2018)
- [Dynamic Metasurface Antennas for MIMO-OFDM Receivers with Bit-Limited ADCs](https://mlsanity.com/paper/1912.06917/) (2019)
- [eSampling: Energy Harvesting ADCs](https://mlsanity.com/paper/2007.08275/) (2020)

## Built on by (most cited first, 7 of 7)

- [Remote Inference over Dynamic Links via Adaptive Rate Deep Task-Oriented Vector Quantization](https://mlsanity.com/paper/2501.02521/) (2025)
- [Neural Augmented Kalman Filtering with Bollinger Bands for Pairs Trading](https://mlsanity.com/paper/2210.15448/) (2022)
- [Limited Communications Distributed Optimization via Deep Unfolded Distributed ADMM](https://mlsanity.com/paper/2309.14353/) (2023)
- [Hardware Implementation of Task-based Quantization in Multi-user Signal Recovery](https://mlsanity.com/paper/2301.11640/) (2023)
- [OLALa: Online Learned Adaptive Lattice Codes for Heterogeneous Federated Learning](https://mlsanity.com/paper/2506.20297/) (2025)
- [Rapid and Power-Aware Learned Optimization for Modular Receive Beamforming](https://mlsanity.com/paper/2408.00439/) (2024)
- [Learning Linear Block Codes with Gradient Quantization](https://mlsanity.com/paper/2503.16169/) (2025)

## Abstract (arXiv)

Analog-to-digital converters (ADCs) allow physical signals to be processed using digital hardware. Their conversion consists of two stages: Sampling, which maps a continuous-time signal into discrete-time, and quantization, i.e., representing the continuous-amplitude quantities using a finite number of bits. ADCs typically implement generic uniform conversion mappings that are ignorant of the task for which the signal is acquired, and can be costly when operating in high rates and fine resolutions. In this work we design task-oriented ADCs which learn from data how to map an analog signal into a digital representation such that the system task can be efficiently carried out. We propose a model for sampling and quantization that facilitates the learning of non-uniform mappings from data. Based on this learnable ADC mapping, we present a mechanism for optimizing a hybrid acquisition system comprised of analog combining, tunable ADCs with fixed rates, and digital processing, by jointly learning its components end-to-end. Then, we show how one can exploit the representation of hybrid acquisition systems as deep network to optimize the sampling rate and quantization rate given the task by utilizing Bayesian meta-learning techniques. We evaluate the proposed deep task-based ADC in two case studies: the first considers symbol detection in multi-antenna digital receivers, where multiple analog signals are simultaneously acquired in order to recover a set of discrete information symbols. The second application is the beamforming of analog channel data acquired in ultrasound imaging. Our numerical results demonstrate that the proposed approach achieves performance which is comparable to operating with high sampling rates and fine resolution quantization, while operating with reduced overall bit rate.