Ghada Sokar
8 papers · 2021–2025 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
π Cross-Pollinator (15) π Conference Polyglot (5) π§ Keyword Pioneer π£ Hot Topic Early Bird π Interdisciplinary Bridge
πΊοΈ
Taxonomy Completionist
(14)
π₯
Unstoppable
(5)
β
The Questioner
Conferences
ICLR (2)
ICML (2)
IJCAI (2)
AISTATS (1)
NIPS (1)
Top co-authors
Keywords
feature selection
(2)
deep reinforcement learning
(2)
continual learning
(1)
catastrophic forgetting
(1)
sample efficiency
(1)
attention mechanism
(1)
continuous control
(1)
lifelong learning
(1)
neural network expressivity
(1)
dynamic sparse training
(1)
dormant neuron
(1)
sparse autoencoder
(1)
sparse training
(1)
sparse neural network
(1)
gradient information
(1)
intelligent agent
(1)
network expressivity
(1)
neural network
(1)
local sensitivity analysis
(1)
network activation
(1)
Papers
Don't flatten, tokenize! Unlocking the key to SoftMoE's efficacy in deep RL
ICLR 2025
Mixtures of Experts Unlock Parameter Scaling for Deep RL
ICML 2024
Supervised Feature Selection via Ensemble Gradient Information from Sparse Neural Networks
AISTATS 2024
The Dormant Neuron Phenomenon in Deep Reinforcement Learning
ICML 2023
Dynamic Sparse Training for Deep Reinforcement Learning
IJCAI 2022
Deep Ensembling with No Overhead for either Training or Testing: The All-Round Blessings of Dynamic Sparsity
ICLR 2022
Where to Pay Attention in Sparse Training for Feature Selection?
NIPS 2022
Continual Lifelong Learning for Intelligent Agents
IJCAI 2021