publications
preprints
- Real-Time Implementation of Machine-Learning DSPProc. Optical Fiber Communication Conf. (OFC), Invited Paper [to Be Presented], San Diego, CA, 2024
- Learning to Extract Distributed Polarization Sensing Data from Noisy Jones MatricesProc. Optical Fiber Communication Conf. (OFC) [to Be Presented], San Diego, CA, 2024
- Semi-Supervised End-to-End Learning for Integrated Sensing and CommunicationsProc. Int. Conf. Mach. Learning for Communication and Networking (ICMLCN) [to Be Presented], Stockholm, Sweden, 2024[arXiv]
- Model-Based End-to-End Learning for Multi-Target Integrated Sensing and Communicationsubmitted to JSTSP, 2023[arXiv]
- Blind Channel Equalization Using Vector-Quantized Variational Autoencoderssubmitted to TCOM, 2023[arXiv]
journals
- End-to-End Learning for VCSEL-based Optical Interconnects: State-of-the-Art, Challenges, and OpportunitiesJ. Lightw. Technol., vol. 41, no. 11, pp. 3261–3277, 2023
- Spatial Signal Design for Positioning via End-to-End LearningIEEE Wireless Commun. Lett., vol. 12, no. 3, pp. 525–529, 2023
- Data-Driven Estimation of Capacity Upper BoundsIEEE Commun. Lett., vol. 26, no. 12, pp. 2939–2943, 2022
- Polarization Tracking in the Presence of PDL and Fast Temporal DriftJ. Lightw. Technol., vol. 40, no. 19, pp. 6408–6416, 2022
- Periodicity-Enabled Size Reduction of Symbol Based Predistortion for High-Order QAMJ. Lightw. Technol., vol. 40, no. 18, pp. 6168–6178, 2022
- Benchmarking and Interpreting End-to-end Learning of MIMO and Multi-User CommunicationIEEE Trans. Wireless Commun., vol. 21, no. 9, pp. 7287–7298, 2022
- Model-Based End-to-End Learning for WDM Systems With Transceiver Hardware ImpairmentsIEEE J. Sel. Topics. Quantum Electron., vol. 28, no. 4, 2022
- Autoencoder-Based Unequal Error Protection CodesIEEE Commun. Lett., vol. 25, no. 11, pp. 3575–3579, 2021
- Pruning and Quantizing Neural Belief Propagation DecodersIEEE J. Sel. Areas Commun., vol. 39, no. 7, pp. 1957–1966, 2021
- Model-Based Machine Learning for Joint Digital Backpropagation and PMD CompensationJ. Lightw. Technol., vol. 39, no. 4, pp. 949–959, 2021
- Physics-Based Deep Learning for Fiber-Optic Communication SystemsIEEE J. Sel. Areas Commun., vol. 39, no. 1, pp. 280–294, 2021
- Revisiting Efficient Multi-Step Nonlinearity Compensation with Machine Learning: An Experimental DemonstrationJ. Lightw. Technol., vol. 38, no. 12, pp. 3114–3124, 2020
- Learning Physical-Layer Communication with Quantized FeedbackIEEE Trans. Commun., vol. 68, no. 1, pp. 645–653, 2020
- Approaching Miscorrection-free Performance of Product Codes with Anchor DecodingIEEE Trans. Commun., vol. 66, no. 7, pp. 2797–2808, 2018
- Density Evolution for Deterministic Generalized Product Codes on the Binary Erasure Channel at High RatesIEEE Trans. Inf. Theory, vol. 63, no. 7, pp. 4357–4378, 2017
- On the Information Loss of the Max-Log Approximation in BICM SystemsIEEE Trans. Inf. Theory, vol. 62, no. 6, pp. 3011–3025, 2016
- Terminated and Tailbiting Spatially Coupled Codes with Optimized Bit Mappings for Spectrally Efficient Fiber-Optical SystemsJ. Lightw. Technol., vol. 33, no. 7, pp. 1275–1285, 2015
- Improving Soft FEC Performance for Higher-Order Modulations via Optimized Bit Channel MappingsOpt. Express, vol. 22, no. 12, pp. 14544–14558, 2014
- A Low-Complexity Detector for Memoryless Polarization-Multiplexed Fiber-Optical ChannelsIEEE Commun. Lett., vol. 18, no. 2, pp. 368–371, 2014
- Design of APSK Constellations for Coherent Optical Channels with Nonlinear Phase NoiseIEEE Trans. Commun., vol. 61, no. 8, pp. 3362–3373, 2013
conference
- Physics-Informed Neural Networks for Studying Charge Dynamics in AirProc. IEEE Conf. Electrical Insulation and Dielectric Phenomena (CEIDP), East Rutherford, NJ, 2023[PDF]
- Model-Driven End-to-End Learning for Integrated Sensing and CommunicationProc. IEEE Int. Conf. Communications (ICC), Rome, Italy, 2023
- FPGA Implementation of Multi-Layer Machine Learning Equalizer with On-Chip TrainingProc. Optical Fiber Communication Conf. (OFC), Los Angeles, CA, 2023
- Rateless Autoencoder Codes: Trading off Decoding Delay and ReliabilityProc. IEEE Int. Conf. Communications (ICC), Rome, Italy, 2023
- Blind Frequency-Domain Equalization Using Vector-Quantized Variational AutoencodersProc. European Conf. Optical Communication (ECOC), Glasgow, UK, 2023
- Improved Polarization Tracking in the Presence of PDLProc. European Conf. Optical Communication (ECOC), Basel, Switzerland, 2022
- Experimental Demonstration of Learned Pulse Shaping Filter for SuperchannelsProc. Optical Fiber Communication Conf. (OFC), Washington, D.C., 2022
- End-to-End Learning for Integrated Sensing and CommunicationProc. IEEE Int. Conf. Communications (ICC), Seoul, South Korea, 2022
- FPGA-based Optical Kerr Effect EmulatorProc. Advanced Photonics Congress (APC), Masstricht, the Netherlands, 2022
- Learning Optimal PAM Levels for VCSEL-based Optical InterconnectsProc. European Conf. Optical Communication (ECOC), Basel, Switzerland, 2022[PDF]
- Symbol-Based Over-the-Air Digital Predistortion Using Reinforcement LearningProc. IEEE Int. Conf. Communications (ICC), Seoul, South Korea, 2022
- Learned Decimation for Neural Belief Propagation DecodersProc. IEEE Int. Conf. Acoustics, Speech and Signal Processing (ICASSP), Toronto, Canada, 2021
- Symbol-Based Supervised Learning Predistortion for Compensating Transmitter NonlinearityProc. European Conf. Optical Communication (ECOC), Bordeaux, France, 2021
- Over-the-Fiber Digital Predistortion Using Reinforcement LearningProc. European Conf. Optical Communication (ECOC), Bordeaux, France, 2021
- End-to-End Autoencoder for Superchannel Transceivers with Hardware ImpairmentProc. Optical Fiber Communication Conf. (OFC), Virtual Conference, 2021
- Pruning Neural Belief Propagation DecodersProc. IEEE Int. Symp. Information Theory (ISIT), Los Angeles, CA, 2020
- End-to-End Learning of Geometrical Shaping Maximizing Generalized Mutual InformationProc. Optical Fiber Communication Conf. (OFC), San Diego, CA, 2020
- Model-Based Machine Learning for Joint Digital Backpropagation and PMD CompensationProc. Optical Fiber Communication Conf. (OFC), San Diego, CA, 2020
- Decoding Reed-Muller Codes Using Redundant Code ConstraintsProc. IEEE Int. Symp. Information Theory (ISIT), Los Angeles, CA, 2020
- Benchmarking End-to-end Learning of MIMO Physical-Layer CommunicationProc. IEEE Glob. Communication Conf. (GLOBECOM), Taipei, Taiwan, 2020
- Reinforcement Learning for Channel Coding: Learned Bit-Flipping DecodingProc. Annual Allerton Conference on Communication, Control, and Computing, Monticello, IL, 2019
- Revisiting Multi-Step Nonlinearity Compensation with Machine LearningProc. European Conf. Optical Communication (ECOC), Dublin, Ireland, 2019
- Learned Belief-Propagation Decoding with Simple Scaling and SNR AdaptationProc. IEEE Int. Symp. Information Theory (ISIT), Paris, France, 2019
- ASIC Implementation of Time-Domain Digital Backpropagation with Deep-Learned Chromatic Dispersion FiltersProc. European Conf. Optical Communication (ECOC), Rome, Italy, 2018
- Wideband Time-Domain Digital Backpropagation via Subband Processing and Deep LearningProc. European Conf. Optical Communication (ECOC), Rome, Italy, 2018
- Deep Learning of the Nonlinear Schrödinger Equation in Fiber-Optic CommunicationsProc. IEEE Int. Symp. Information Theory (ISIT), Vail, CO, 2018
- Nonlinear Interference Mitigation via Deep Neural NetworksProc. Optical Fiber Communication Conf. (OFC), San Diego, CA, 2018
- What Can Machine Learning Teach Us about Communications?Proc. IEEE Information Theory Workshop (ITW), Guangzhou, China, 2018
- Decoding Reed-Muller Codes Using Minimum-Weight Parity ChecksProc. IEEE Int. Symp. Information Theory (ISIT), Vail, CO, 2018
- On Low-Complexity Decoding of Product Codes for High-Throughput Fiber-Optic SystemsProc. Int. Symp. Turbo Codes and Iterative Information Processing (ISTC), Hong Kong, 2018
- Achievable Information Rates for Nonlinear Fiber Communication via End-to-end Autoencoder LearningProc. European Conf. Optical Communication (ECOC), Rome, Italy, 2018
- Miscorrection-Free Decoding of Staircase CodesProc. European Conf. Optical Communication (ECOC), Gothenburg, Sweden, 2017
- Deterministic and Ensemble-Based Spatially-Coupled Product CodesProc. IEEE Int. Symp. Information Theory (ISIT), Barcelona, Spain, 2016
- Density Evolution for Deterministic Generalized Product Codes with Higher-Order ModulationProc. Int. Symp. Turbo Codes and Iterative Information Processing (ISTC), Brest, France, 2016
- A Deterministic Construction and Density Evolution Analysis for Generalized Product CodesProc. Int. Zurich Seminar on Communications (IZS), Zürich, Switzerland, 2016
- Density Evolution and Error Floor Analysis of Staircase and Braided CodesProc. Optical Fiber Communication Conf. (OFC), Anaheim, CA, 2016
- Spatially-Coupled Codes for Optical Communications: State-of-the-Art and Open ProblemsProc. Optoelectronics and Communications Conf. (OECC), Shanghai, China, 2015
- On Parameter Optimization for Staircase CodesProc. Optical Fiber Communication Conf. (OFC), Los Angeles, CA, 2015
- Comparison of Terminated and Tailbiting Spatially Coupled LDPC Codes With Optimized Bit Mapping for PM-64-QAMProc. European Conf. Optical Communication (ECOC), Cannes, France, 2014
- Optimized Bit Mappings for Spatially Coupled LDPC Codes over Parallel Binary Erasure ChannelsProc. IEEE Int. Conf. Communications (ICC), Sydney, Australia, 2014
- Constellation Optimization for Coherent Optical Channels Distorted by Nonlinear Phase NoiseProc. IEEE Glob. Communication Conf. (GLOBECOM), Anaheim, CA, 2012
Patents
- Systems and methods for decoding forward error correction codes based on component codes[PDF]
Thesis
- Analysis and Design of Spatially-Coupled Codes with Application to Fiber-Optical CommunicationsPhD thesis, Chalmers University of Technology, May 2016
- On Signal Constellations and Coding for Long-Haul Fiber-Optical SystemsLicentiate thesis, Chalmers University of Technology, April 2014
- Bidirectional Wireless Communication via Relay Nodes using LatticesDiploma thesis, Ulm University, July 2011[PDF]
- Turbo Equalization Performance: The Effect of Precoding and Application of Turbo CodesStudy thesis, Ulm University, 2009[PDF]
Disclaimer: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author’s copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.