Research Interests

Task-aware compression in communication systems

Related work:

  • Learning-Based Compress-and-Forward Schemes for the Relay Channel
    E. Ozyilkan, F. Carpi, S. Garg, E. Erkip  —  preprint
    arXiv

  • Neural Compress-and-Forward for the Relay Channel
    E. Ozyilkan, F. Carpi, S. Garg, E. Erkip  —  SPAWC 2024
    DOI | arXiv | Poster

  • Precoding-oriented Massive MIMO CSI Feedback Design
    F. Carpi, S. Venkatesan, J. Du, H. Viswanathan, S. Garg, E. Erkip  —  ICC 2023
    DOI | arXiv | Slides | Poster

  • Single-Shot Compression for Hypothesis Testing
    F. Carpi, S. Garg, E. Erkip  —  SPAWC 2021 , ITR3 @ ICML 2021, NASIT 2021, CTW 2021
    *** Best Student Paper Award (2nd place) at IEEE SPAWC 2021.
    *** Best Poster Award (1st place) at IEEE CTW 2021.
    DOI | arXiv | Poster | Slides | Video

  • Learned Task-Aware Compression Methods in Communication Systems
    F. Carpi  —  Ph.D. Thesis 2024
    Dissertation | Slides

Waveform optimization

Related work:

  • Learned Pulse Shaping Design for PAPR Reduction in DFT-s-OFDM
    F. Carpi, S. Rostami, J. Cho, S. Garg, E. Erkip, C. J. Zhang  —  SPAWC 2024
    DOI | arXiv | Poster

Machine learning for channel decoding

Related work:

  • Reinforcement Learning for Channel Coding: Learned Bit-Flipping Decoding
    F. Carpi, C. Häger, M. Martalò, R. Raheli, H. D. Pfister  —  Allerton 2019
    DOI | arXiv | Slides | Github

  • Learned Belief-Propagation Decoding with Simple Scaling and SNR Adaptation
    M. Lian, F. Carpi, C. Häger, H. D. Pfister  —  ISIT 2019
    DOI | arXiv

  • Exploring Machine Learning Algorithms for Decoding Linear Block Codes
    F. Carpi  —  MS Thesis 2018
    Thesis | Summary | Slides

Localization

Related work:

  • Experimental Analysis of RSSI-based Localization Algorithms with NLOS Pre-Mitigation for IoT Applications
    F. Carpi, M. Martalò, L. Davoli, A. Cilfone, Y. Yu, Y. Wang, G. Ferrari  —  ComNet 2023
    DOI

  • RSSI-based Methods for LOS/NLOS Channel Identification in Indoor Scenarios
    F. Carpi, L. Davoli, M. Martalò, A. Cilfone, Y. Yu, Y. Wang, G. Ferrari  —  ISWCS 2019
    DOI