Publications
Exhaustive, reverse chronological order.
Conference proceedings.
[C9]
On the suboptimality of linear codes for binary distributed hypothesis testing
[arXiv]
A.G., Robinson D. H. Cung, Emre Telatar
ISIT (IEEE International Symposium on Information Theory) 2026 (to appear)
A.G., Robinson D. H. Cung, Emre Telatar
ISIT (IEEE International Symposium on Information Theory) 2026 (to appear)
[C8]
High signal-to-noise ratio asymptotics of entropy-constrained Gaussian channel capacity
[arXiv]
A.G., Shlomo Shamai (Shitz), Emre Telatar
ISIT (IEEE International Symposium on Information Theory) 2026 (to appear)
A.G., Shlomo Shamai (Shitz), Emre Telatar
ISIT (IEEE International Symposium on Information Theory) 2026 (to appear)
[C7]
On entropy-constrained Gaussian channel capacity via the moment problem
[arXiv]
A.G., Shlomo Shamai (Shitz), Emre Telatar
ISIT (IEEE International Symposium on Information Theory) 2025
A.G., Shlomo Shamai (Shitz), Emre Telatar
ISIT (IEEE International Symposium on Information Theory) 2025
[C6]
Attention with Markov: A curious case of single-layer transformers
[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)
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)
[C5]
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)]
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)]
[C4]
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)
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)
[C3]
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
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
[C2]
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
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
[C1]
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
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
Separated by area.
Information theory (Shannon theory, information measures, hypothesis testing; 2022--present).
[C9]
On the suboptimality of linear codes for binary distributed hypothesis testing
[arXiv]
A.G., Robinson D. H. Cung, Emre Telatar
ISIT (IEEE International Symposium on Information Theory) 2026 (to appear)
A.G., Robinson D. H. Cung, Emre Telatar
ISIT (IEEE International Symposium on Information Theory) 2026 (to appear)
[C8]
High signal-to-noise ratio asymptotics of entropy-constrained Gaussian channel capacity
[arXiv]
A.G., Shlomo Shamai (Shitz), Emre Telatar
ISIT (IEEE International Symposium on Information Theory) 2026 (to appear)
A.G., Shlomo Shamai (Shitz), Emre Telatar
ISIT (IEEE International Symposium on Information Theory) 2026 (to appear)
[C7]
On entropy-constrained Gaussian channel capacity via the moment problem
[arXiv]
A.G., Shlomo Shamai (Shitz), Emre Telatar
ISIT (IEEE International Symposium on Information Theory) 2025
A.G., Shlomo Shamai (Shitz), Emre Telatar
ISIT (IEEE International Symposium on Information Theory) 2025
Machine learning (Transformers/LLMs, bandits; 2022--24).
[C6]
Attention with Markov: A curious case of single-layer transformers
[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)
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)
[C5]
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)]
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)]
[C4]
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)
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)
[C3]
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
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
Signal processing (micro-Doppler parameter estimation; 2020--22).
[C2]
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
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
[C1]
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
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