On entropy-constrained Gaussian channel capacity via the moment problem[arXiv]
A. G., Shlomo Shamai (Shitz), Emre Telatar
Under review
Conference proceedings/Workshop papers
Fundamental limits of prompt compression: A rate-distortion framework for black-box language models[arXiv]
Alliot Nagle*, A. G.*, Marco Bondaschi, Michael Gastpar, Ashok Vardhan Makkuva, Hyeji Kim
NeurIPS 2024
Also at ICML 2024 Workshop on Theoretical Foundations of Foundation Models (TF2M)
[Oral (top 4 out of 58)]
Local to global: Learning dynamics and effect of initialization for transformers[arXiv]
Ashok Vardhan Makkuva*, Marco Bondaschi*, Chanakya Ekbote, A. G., Alliot Nagle, Hyeji Kim, Michael Gastpar
NeurIPS 2024
Also at ICML 2024 Workshop on Theoretical Foundations of Foundation Models (TF2M)
Attention with Markov: A framework for principled analysis of transformers via Markov chains[arXiv]
Ashok Vardhan Makkuva*, Marco Bondaschi*, A. G., Alliot Nagle, Martin Jaggi, Hyeji Kim, Michael Gastpar
ICLR 2025 [Spotlight (top 5%)]
Also at ICML 2024 Workshop on Mechanistic Interpretability (MI)
ICQ: A quantization scheme for best-arm identification over bit-constrained channels[IEEE Xplore][arXiv]
Fathima Z. Faizal, A. G., Manjesh K. Hanawal, Nikhil Karamchandani
WiOpt (International Symposium on Modeling and Optimization in Mobile, Ad hoc, and Wireless Networks) 2023
Micro-Doppler parameter estimation using variational mode decomposition with finite rate of innovation[IEEE Xplore]
Shrikant Sharma, A. G., Darin Jeff, Garweet Sresth, Sanket Bhalerao, Vikram M. Gadre, C. H. Srinivas Rao, P. Radhakrishna
SPCOM (IEEE International Conference on Signal Processing and Communications) 2022
Theoretical analysis of an inverse Radon transform based multicomponent micro-Doppler parameter estimation algorithm[IEEE Xplore]
Shrikant Sharma, A. G., Nikhar P. Rakhashia, Vikram M. Gadre, Shaan ul Haque, Aseer Ansari, Ram Bilas Pachori,
P. Radhakrishna, Peeyush Sahay
NCC (National Conference on Communications) 2022