Mike Rabbat
8 papers · 2019–2024 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
π Interdisciplinary Bridge π§ Keyword Pioneer π£ Hot Topic Early Bird π Conference Polyglot (4) π Academic Marathon (5)
π
Cross-Pollinator
(12)
π
Renaissance Researcher
(7)
πΊοΈ
Taxonomy Completionist
(17)
Conferences
ICML (4)
AISTATS (2)
NIPS (1)
UAI (1)
Top co-authors
Research topics
Keywords
federated learning
(3)
distributed optimization
(2)
differential privacy
(2)
gradient descent
(2)
convergence analysis
(2)
distributed learning
(2)
generalization error
(1)
stochastic approximation
(1)
partial observability
(1)
secure aggregation
(1)
communication efficiency
(1)
empirical risk
(1)
hessian eigenvalue
(1)
implicit bia
(1)
next-token prediction
(1)
non-iid datum
(1)
client-server architecture
(1)
reversal curse
(1)
nesterov acceleration
(1)
asynchronous aggregation
(1)
Papers
The Factorization Curse: Which Tokens You Predict Underlie the Reversal Curse and More
NIPS 2024
Federated Learning with Buffered Asynchronous Aggregation
AISTATS 2022
Privacy-aware compression for federated data analysis
UAI 2022
Federated Learning with Partial Model Personalization
ICML 2022
Learning with Gradient Descent and Weakly Convex Losses
AISTATS 2021
On the Convergence of Nesterovβs Accelerated Gradient Method in Stochastic Settings
ICML 2020
TarMAC: Targeted Multi-Agent Communication
ICML 2019
Stochastic Gradient Push for Distributed Deep Learning
ICML 2019