Zahra Atashgahi

5 papers · 2021–2024 · 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 🗺️ Taxonomy Completionist (12) 🐣 Hot Topic Early Bird ❓ The Questioner

Venues

NeurIPS (2) AISTATS (1) ICLR (1) IJCAI (1)

Top co-authors

Decebal Constantin Mocanu (4) Mykola Pechenizkiy (4) Ghada Sokar (3) Tianlong Chen (2) Zhangyang Wang (2) Xiaohan Chen (2) Shiwei Liu (2) Lu Yin (1) Li Shen (1) Huanyu Kou (1)

Research topics

Machine Learning (4) Deep Learning (3) Learning Types · Machine Learning (2) Techniques (2) Application Areas (1) Architectures (1) Core Methods (1) Learning Types · Deep Learning (1) Optimization & Theory · Machine Learning (1) Optimization & Theory · Deep Learning (1)

Keywords

sparse training (2) sparse neural network (2) feature selection (2) attention mechanism (1) deep neural network (1) uncertainty estimation (1) sparse autoencoder (1) inference efficiency (1) gradient information (1) deep ensemble (1) out-of-distribution robustness (1) dynamic sparsity (1) computational resource (1) local sensitivity analysis (1) cost-effective neural network (1) gradual magnitude pruning (1) model compression (1) pruning plasticity (1) unsupervised learning (1) lottery ticket hypothesis (1)

Papers

Supervised Feature Selection via Ensemble Gradient Information from Sparse Neural Networks AISTATS 2024 Cost-effective Artificial Neural Networks IJCAI 2023 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? NeurIPS 2022 Sparse Training via Boosting Pruning Plasticity with Neuroregeneration NeurIPS 2021