Michael Gastpar
12 papers · 2021–2025 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+6 more ↓ Show less ↑
π£ Hot Topic Early Bird π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (10) π§ Keyword Pioneer π Conference Polyglot (5)
π
Interdisciplinary Bridge
πΊοΈ
Taxonomy Completionist
(10)
π
Triple Crown
β‘
Prolific Year
(7)
π₯
Unstoppable
(5)
π
Century Club
(12)
Conferences
ICLR (3)
ICML (3)
NIPS (3)
JMLR (2)
COLT (1)
Top co-authors
Research topics
Keywords
information theory
(2)
differential privacy
(1)
sequence modeling
(1)
parameter estimation
(1)
attention mechanism
(1)
in-context learning
(1)
efficient inference
(1)
renyi divergence
(1)
generalization error
(1)
markov chain
(1)
total variation
(1)
rate distortion
(1)
local privacy
(1)
distribution learning
(1)
randomized response
(1)
lower bound
(1)
learning dynamics
(1)
next-token prediction
(1)
stochastic gradient langevin dynamics
(1)
parameter initialization
(1)
Papers
Attention with Markov: A Curious Case of Single-layer Transformers
ICLR 2025
Leveraging Sparsity for Sample-Efficient Preference Learning: A Theoretical Perspective
ICML 2025
Transformers on Markov data: Constant depth suffices
NIPS 2024
Fantastic Generalization Measures are Nowhere to be Found
ICLR 2024
Lower Bounds on the Bayesian Risk via Information Measures
JMLR 2024
Fundamental Limits of Prompt Compression: A Rate-Distortion Framework for Black-Box Language Models
NIPS 2024
LASER: Linear Compression in Wireless Distributed Optimization
ICML 2024
The Fundamental Limits of Least-Privilege Learning
ICML 2024
Local to Global: Learning Dynamics and Effect of Initialization for Transformers
NIPS 2024
Generalization Error Bounds for Noisy, Iterative Algorithms via Maximal Leakage
COLT 2023
A Johnson-Lindenstrauss Framework for Randomly Initialized CNNs
ICLR 2022
Locally Differentially-Private Randomized Response for Discrete Distribution Learning
JMLR 2021