Milad Sefidgaran
6 papers · 2021–2025 · 4 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(11)
🔥
Unstoppable · Bronze
Venues
Top co-authors
Research topics
Keywords
generalization bound
(3)
rate-distortion theory
(3)
support vector machine
(2)
representation learning
(2)
mutual information
(2)
generalization error
(2)
minimum description length
(2)
fractal dimension
(1)
heavy-tailed distribution
(1)
generalization guarantee
(1)
variational information bottleneck
(1)
lossless compression
(1)
stochastic gradient langevin dynamics
(1)
overparameterized network
(1)
gaussian mixture
(1)
stochastic learning
(1)
compression framework
(1)
heavy tail
(1)
source coding
(1)
communication round
(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
NeurIPS 2023
Rate-Distortion Theoretic Bounds on Generalization Error for Distributed Learning
NeurIPS 2022
Rate-Distortion Theoretic Generalization Bounds for Stochastic Learning Algorithms
COLT 2022
Heavy Tails in SGD and Compressibility of Overparametrized Neural Networks
NeurIPS 2021