Gastpar, Michael

21 publications

ICLR 2025 Attention with Markov: A Curious Case of Single-Layer Transformers Ashok Vardhan Makkuva, Marco Bondaschi, Adway Girish, Alliot Nagle, Martin Jaggi, Hyeji Kim, Michael Gastpar

ICLRW 2025 From Markov to Laplace: How Mamba In-Context Learns Markov Chains Marco Bondaschi, Nived Rajaraman, Xiuying Wei, Kannan Ramchandran, Razvan Pascanu, Caglar Gulcehre, Michael Gastpar, Ashok Vardhan Makkuva

ICML 2025 Leveraging Sparsity for Sample-Efficient Preference Learning: A Theoretical Perspective Yunzhen Yao, Lie He, Michael Gastpar

NeurIPS 2025 What One Cannot, Two Can: Two-Layer Transformers Provably Represent Induction Heads on Any-Order Markov Chains Chanakya Ekbote, Ashok Vardhan Makkuva, Marco Bondaschi, Nived Rajaraman, Michael Gastpar, Jason D. Lee, Paul Pu Liang

NeurIPS 2025 Which Algorithms Have Tight Generalization Bounds? Michael Gastpar, Ido Nachum, Jonathan Shafer, Thomas Weinberger

NeurIPS 2025 Zip2zip: Inference-Time Adaptive Tokenization via Online Compression Saibo Geng, Nathan Ranchin, Yunzhen Yao, Maxime Peyrard, Chris Wendler, Michael Gastpar, Robert West

ICMLW 2024 Attention with Markov: A Curious Case of Single-Layer Transformers Ashok Vardhan Makkuva, Marco Bondaschi, Alliot Nagle, Adway Girish, Hyeji Kim, Martin Jaggi, Michael Gastpar

ICLR 2024 Fantastic Generalization Measures Are Nowhere to Be Found Michael Gastpar, Ido Nachum, Jonathan Shafer, Thomas Weinberger

NeurIPS 2024 Fundamental Limits of Prompt Compression: A Rate-Distortion Framework for Black-Box Language Models Alliot Nagle, Adway Girish, Marco Bondaschi, Michael Gastpar, Ashok Vardhan Makkuva, Hyeji Kim

ICMLW 2024 Fundamental Limits of Prompt Compression: A Rate-Distortion Framework for Black-Box Language Models Adway Girish, Alliot Nagle, Ashok Vardhan Makkuva, Marco Bondaschi, Michael Gastpar, Hyeji Kim

ICML 2024 LASER: Linear Compression in Wireless Distributed Optimization Ashok Vardhan Makkuva, Marco Bondaschi, Thijs Vogels, Martin Jaggi, Hyeji Kim, Michael Gastpar

NeurIPS 2024 Local to Global: Learning Dynamics and Effect of Initialization for Transformers Ashok Vardhan Makkuva, Marco Bondaschi, Chanakya Ekbote, Adway Girish, Alliot Nagle, Hyeji Kim, Michael Gastpar

ICMLW 2024 Local to Global: Learning Dynamics and Effect of Initialization for Transformers Ashok Vardhan Makkuva, Marco Bondaschi, Chanakya Ekbote, Adway Girish, Alliot Nagle, Hyeji Kim, Michael Gastpar

JMLR 2024 Lower Bounds on the Bayesian Risk via Information Measures Amedeo Roberto Esposito, Adrien Vandenbroucque, Michael Gastpar

ICML 2024 The Fundamental Limits of Least-Privilege Learning Theresa Stadler, Bogdan Kulynych, Michael Gastpar, Nicolas Papernot, Carmela Troncoso

NeurIPS 2024 Transformers on Markov Data: Constant Depth Suffices Nived Rajaraman, Marco Bondaschi, Kannan Ramchandran, Michael Gastpar, Ashok Vardhan Makkuva

ICMLW 2024 Transformers on Markov Data: Constant Depth Suffices Nived Rajaraman, Marco Bondaschi, Ashok Vardhan Makkuva, Kannan Ramchandran, Michael Gastpar

COLT 2023 Generalization Error Bounds for Noisy, Iterative Algorithms via Maximal Leakage Ibrahim Issa, Amedeo Roberto Esposito, Michael Gastpar

NeurIPSW 2023 LASER: Linear Compression in Wireless Distributed Optimization Ashok Vardhan Makkuva, Marco Bondaschi, Thijs Vogels, Martin Jaggi, Hyeji Kim, Michael Gastpar

ICLR 2022 A Johnson-Lindenstrauss Framework for Randomly Initialized CNNs Ido Nachum, Jan Hazla, Michael Gastpar, Anatoly Khina

JMLR 2021 Locally Differentially-Private Randomized Response for Discrete Distribution Learning Adriano Pastore, Michael Gastpar