Ashok Vardhan Makkuva

36 papers A* 9A 2B 4Journal 21

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	TERMINATOR: Learning Optimal Exit Points for Early Stopping in Chain-of-Thought Reasoning. CoRR Alliot Nagle, Jakhongir Saydaliev, Dhia Garbaya, Michael Gastpar, Ashok Vardhan Makkuva, Hyeji Kim
2025	A*	`conf`	Attention with Markov: A Curious Case of Single-layer Transformers. ICLR Ashok Vardhan Makkuva, Marco Bondaschi, Adway Girish, Alliot Nagle, Martin Jaggi, Hyeji Kim, Michael Gastpar
2025	J	`jnl`	From Markov to Laplace: How Mamba In-Context Learns Markov Chains. CoRR Marco Bondaschi, Nived Rajaraman, Xiuying Wei, Kannan Ramchandran, Razvan Pascanu, Caglar Gulcehre, Michael Gastpar, Ashok Vardhan Makkuva
2025	J	`jnl`	What One Cannot, Two Can: Two-Layer Transformers Provably Represent Induction Heads on Any-Order Markov Chains. CoRR Chanakya Ekbote, Marco Bondaschi, Nived Rajaraman, Jason D. Lee, Michael Gastpar, Ashok Vardhan Makkuva, Paul Pu Liang
2024	J	`jnl`	Attention with Markov: A Framework for Principled Analysis of Transformers via Markov Chains. CoRR Ashok Vardhan Makkuva, Marco Bondaschi, Adway Girish, Alliot Nagle, Martin Jaggi, Hyeji Kim, Michael Gastpar
2024	A*	`conf`	Fundamental Limits of Prompt Compression: A Rate-Distortion Framework for Black-Box Language Models. NeurIPS Alliot Nagle, Adway Girish, Marco Bondaschi, Michael Gastpar, Ashok Vardhan Makkuva, Hyeji Kim
2024	J	`jnl`	Fundamental Limits of Prompt Compression: A Rate-Distortion Framework for Black-Box Language Models. CoRR Adway Girish, Alliot Nagle, Marco Bondaschi, Michael Gastpar, Ashok Vardhan Makkuva, Hyeji Kim
2024	A*	`conf`	LASER: Linear Compression in Wireless Distributed Optimization. ICML Ashok Vardhan Makkuva, Marco Bondaschi, Thijs Vogels, Martin Jaggi, Hyeji Kim, Michael Gastpar
2024	A*	`conf`	Local to Global: Learning Dynamics and Effect of Initialization for Transformers. NeurIPS Ashok Vardhan Makkuva, Marco Bondaschi, Adway Girish, Alliot Nagle, Hyeji Kim, Michael Gastpar, Chanakya Ekbote
2024	J	`jnl`	Local to Global: Learning Dynamics and Effect of Initialization for Transformers. CoRR Ashok Vardhan Makkuva, Marco Bondaschi, Chanakya Ekbote, Adway Girish, Alliot Nagle, Hyeji Kim, Michael Gastpar
2024	J	`jnl`	Transformers on Markov Data: Constant Depth Suffices. CoRR Nived Rajaraman, Marco Bondaschi, Kannan Ramchandran, Michael Gastpar, Ashok Vardhan Makkuva
2024	A*	`conf`	Transformers on Markov data: Constant depth suffices. NeurIPS Nived Rajaraman, Marco Bondaschi, Ashok Vardhan Makkuva, Kannan Ramchandran, Michael Gastpar
2023	A*	`conf`	CRISP: Curriculum based Sequential neural decoders for Polar code family. ICML S. Ashwin Hebbar, Viraj Vivek Nadkarni, Ashok Vardhan Makkuva, Suma Bhat, Sewoong Oh, Pramod Viswanath
2023	J	`jnl`	LASER: Linear Compression in Wireless Distributed Optimization. CoRR Ashok Vardhan Makkuva, Marco Bondaschi, Thijs Vogels, Martin Jaggi, Hyeji Kim, Michael C. Gastpar
2023	J	`jnl`	Machine Learning-Aided Efficient Decoding of Reed-Muller Subcodes. CoRR Mohammad Vahid Jamali, Xiyang Liu, Ashok Vardhan Makkuva, Hessam Mahdavifar, Sewoong Oh, Pramod Viswanath
2023	J	`jnl`	Machine Learning-Aided Efficient Decoding of Reed-Muller Subcodes. IEEE J. Sel. Areas Inf. Theory Mohammad Vahid Jamali, Xiyang Liu, Ashok Vardhan Makkuva, Hessam Mahdavifar, Sewoong Oh, Pramod Viswanath
2022	J	`jnl`	CRISP: Curriculum based Sequential Neural Decoders for Polar Code Family. CoRR S. Ashwin Hebbar, Viraj Nadkarni, Ashok Vardhan Makkuva, Suma Bhat, Sewoong Oh, Pramod Viswanath
2022	B	`conf`	TinyTurbo: Efficient Turbo Decoders on Edge. ISIT S. Ashwin Hebbar, Rajesh K. Mishra, Sravan Kumar Ankireddy, Ashok Vardhan Makkuva, Hyeji Kim, Pramod Viswanath
2022	J	`jnl`	TinyTurbo: Efficient Turbo Decoders on Edge. CoRR S. Ashwin Hebbar, Rajesh K. Mishra, Sravan Kumar Ankireddy, Ashok Vardhan Makkuva, Hyeji Kim, Pramod Viswanath
2021	J	`jnl`	KO codes: Inventing Nonlinear Encoding and Decoding for Reliable Wireless Communication via Deep-learning. CoRR Ashok Vardhan Makkuva, Xiyang Liu, Mohammad Vahid Jamali, Hessam Mahdavifar, Sewoong Oh, Pramod Viswanath
2021	A*	`conf`	KO codes: inventing nonlinear encoding and decoding for reliable wireless communication via deep-learning. ICML Ashok Vardhan Makkuva, Xiyang Liu, Mohammad Vahid Jamali, Hessam Mahdavifar, Sewoong Oh, Pramod Viswanath
2021	B	`conf`	Reed-Muller Subcodes: Machine Learning-Aided Design of Efficient Soft Recursive Decoding. ISIT Mohammad Vahid Jamali, Xiyang Liu, Ashok Vardhan Makkuva, Hessam Mahdavifar, Sewoong Oh, Pramod Viswanath
2021	J	`jnl`	Reed-Muller Subcodes: Machine Learning-Aided Design of Efficient Soft Recursive Decoding. CoRR Mohammad Vahid Jamali, Xiyang Liu, Ashok Vardhan Makkuva, Hessam Mahdavifar, Sewoong Oh, Pramod Viswanath
2020	A	`conf`	Learning in Gated Neural Networks. AISTATS Ashok Vardhan Makkuva, Sewoong Oh, Sreeram Kannan, Pramod Viswanath
2020	A*	`conf`	Optimal transport mapping via input convex neural networks. ICML Ashok Vardhan Makkuva, Amirhossein Taghvaei, Sewoong Oh, Jason D. Lee
2019	B	`conf`	Barracuda: The Power of ℓ-polling in Proof-of-Stake Blockchains. MobiHoc Giulia Fanti, Jiantao Jiao, Ashok Vardhan Makkuva, Sewoong Oh, Ranvir Rana, Pramod Viswanath
2019	J	`jnl`	Barracuda: The Power of 𝓁-polling in Proof-of-Stake Blockchains. CoRR Giulia Fanti, Jiantao Jiao, Ashok Vardhan Makkuva, Sewoong Oh, Ranvir Rana, Pramod Viswanath
2019	A*	`conf`	Breaking the gridlock in Mixture-of-Experts: Consistent and Efficient Algorithms. ICML Ashok Vardhan Makkuva, Pramod Viswanath, Sreeram Kannan, Sewoong Oh
2019	A	`conf`	Learning One-hidden-layer Neural Networks under General Input Distributions. AISTATS Weihao Gao, Ashok Vardhan Makkuva, Sewoong Oh, Pramod Viswanath
2019	J	`jnl`	Learning in Gated Neural Networks. CoRR Ashok Vardhan Makkuva, Sewoong Oh, Sreeram Kannan, Pramod Viswanath
2019	J	`jnl`	Optimal transport mapping via input convex neural networks. CoRR Ashok Vardhan Makkuva, Amirhossein Taghvaei, Sewoong Oh, Jason D. Lee
2018	J	`jnl`	Equivalence of Additive-Combinatorial Linear Inequalities for Shannon Entropy and Differential Entropy. IEEE Trans. Inf. Theory Ashok Vardhan Makkuva, Yihong Wu
2018	J	`jnl`	Globally Consistent Algorithms for Mixture of Experts. CoRR Ashok Vardhan Makkuva, Sreeram Kannan, Pramod Viswanath
2018	J	`jnl`	Learning One-hidden-layer Neural Networks under General Input Distributions. CoRR Weihao Gao, Ashok Vardhan Makkuva, Sewoong Oh, Pramod Viswanath
2016	B	`conf`	On additive-combinatorial affine inequalities for Shannon entropy and differential entropy. ISIT Ashok Vardhan Makkuva, Yihong Wu
2016	J	`jnl`	On additive-combinatorial affine inequalities for Shannon entropy and differential entropy. CoRR Ashok Vardhan Makkuva, Yihong Wu