Milad Sefidgaran
6 papers · 2021–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
π
Conference Polyglot
(4)
π
Interdisciplinary Bridge
πΊοΈ
Taxonomy Completionist
(10)
π
Cross-Pollinator
(15)
π₯
Unstoppable
(5)
Conferences
NIPS (3)
COLT (1)
ICLR (1)
ICML (1)
Top co-authors
Keywords
mutual information
(2)
generalization bound
(2)
rate-distortion theory
(2)
information bottleneck
(1)
distributed learning
(1)
generalization error
(1)
minimum description length
(1)
support vector machine
(1)
fractal dimension
(1)
heavy-tailed distribution
(1)
generalization guarantee
(1)
lossless compression
(1)
stochastic gradient langevin dynamics
(1)
overparameterized network
(1)
stochastic learning
(1)
compression framework
(1)
neural network compression
(1)
heavy tail
(1)
representation learning
(1)
stochastic gradient descent
(1)
Papers
Generalization Guarantees for Representation Learning via Data-Dependent Gaussian Mixture Priors
ICLR 2025
Lessons from Generalization Error Analysis of Federated Learning: You May Communicate Less Often!
ICML 2024
Minimum Description Length and Generalization Guarantees for Representation Learning
NIPS 2023
Rate-Distortion Theoretic Bounds on Generalization Error for Distributed Learning
NIPS 2022
Rate-Distortion Theoretic Generalization Bounds for Stochastic Learning Algorithms
COLT 2022
Heavy Tails in SGD and Compressibility of Overparametrized Neural Networks
NIPS 2021