Olga Saukh

4 papers · 2022–2025 · 2 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 (11) 🐣 Hot Topic Early Bird 👥 Mega-Team · Squad

Venues

ICLR (3) NeurIPS (1)

Top co-authors

Rahim Entezari (3) Behnam Neyshabur (2) Hanie Sedghi (2) Jenia Jitsev (1) Sarah Pratt (1) Georgios Smyrnis (1) Thao Nguyen (1) Mehdi Cherti (1) Yair Carmon (1) Dhruba Ghosh (1)

Research topics

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

Keywords

permutation invariance (2) lottery ticket hypothesis (1) stochastic gradient descent (1) zero-shot learning (1) k-means clustering (1) neural network optimization (1) ensemble method (1) multimodal dataset (1) image-text pair (1) linear mode connectivity (1) normalization layer (1) clip model (1) data filtering (1) zero-shot accuracy (1) linear interpolation (1) dataset filtering (1) data-free compression (1) neural network (1) network folding (1) variance collapse (1)

Papers

Forget the Data and Fine-Tuning! Just Fold the Network to Compress ICLR 2025 DataComp: In search of the next generation of multimodal datasets NeurIPS 2023 REPAIR: REnormalizing Permuted Activations for Interpolation Repair ICLR 2023 The Role of Permutation Invariance in Linear Mode Connectivity of Neural Networks ICLR 2022