Contact

  • Academic
    abhiramg@stanford.edu
    University - Student Department: Electrical Engineering Position: Graduate

Additional Info

  • Mail Code: 9505

All Publications

  • Information-computation trade-offs in nonlinear transforms. Philosophical transactions. Series A, Mathematical, physical, and engineering sciences Ding, C., Gorle, A., Jeong, J., Sagan, N., Weissman, T. 2026; 384 (2315)

    Abstract

    In this work, we explore the interplay between information and computation in nonlinear transform-based compression for broad classes of modern information-processing tasks. We first investigate two emerging nonlinear data transformation frameworks for image compression: implicit neural representations (INRs) and two-dimensional (2D) Gaussian splatting (GS). We analyse their representational properties, behaviour under lossy compression and convergence dynamics. Our results highlight key trade-offs between INR's compact, resolution-flexible neural field representations and GS's highly parallelizable, spatially interpretable fitting, providing insights for future hybrid and compression-aware frameworks. Next, we introduce the textual transform that enables efficient compression at ultra-low bit rates-regimes, and simultaneously enhances human perceptual satisfaction. When combined with the concept of denoising via lossy compression, the textual transform becomes a powerful tool for denoising tasks. Finally, we describe a Lempel-Ziv (LZ, specifically LZ78) transform, a universal method that, when applied to any member of a broad compressor family, produces new compressors that retain the asymptotic universality guarantees of the LZ78 algorithm. Collectively, these three transforms illuminate the fundamental trade-offs between coding efficiency and computational cost. We discuss how these insights extend beyond compression to tasks such as classification, denoising and generative AI, suggesting new pathways for using nonlinear transformations to balance resource constraints and performance. This article is part of the discussion meeting issue 'Bits, neurons and qubits for sustainable AI'.

    View details for DOI 10.1098/rsta.2024.0509

    View details for PubMedID 41762746

  • AI Enabled 6G for Semantic Metaverse: Prospects, Challenges and Solutions for Future Wireless VR IEEE WIRELESS COMMUNICATIONS Mohsin, M., Bhattacharya, S., Gorle, A. R., Jamshed, M., Cioffi, J. M. 2025; 32 (5): 72-79

    View details for DOI 10.1109/MWC.001.2500045

    View details for Web of Science ID 001579023100002

  • LZMidi: Compression-Based Symbolic Music Generation Ding, C., Gorle, A., Bhattacharya, S., Hasteer, D., Sagan, N., Weissman, T., IEEE IEEE. 2025

    View details for DOI 10.1109/ISIT63088.2025.11195229

    View details for Web of Science ID 001821502600022

  • minPIC: Optimal Power Allocation in Multi-User Interference Channels Bhattacharya, S., Gorle, A., Cioffi, J. M., IEEE IEEE. 2025: 3927-3932

    View details for DOI 10.1109/GLOBECOM59602.2025.11432474

    View details for Web of Science ID 001810917600111

  • AoI-QPS: Age-of-Information Aware Efficient Queue-Proportional Scheduling Gorle, A., Bhattacharya, S., Cioffi, J. M., IEEE IEEE. 2025: 4607-4612

    View details for DOI 10.1109/GLOBECOM59602.2025.11431983

    View details for Web of Science ID 001810917600223