Scholar
Liane Galanti
Google Scholar ID: 8jDgDJIAAAAJ
CS PhD Student @ Princeton
Citations & Impact
Citations
50
H-index
3
i10-index
2
Publications
6
Co-authors
8
list available
Contact
Publications
Resume (English only)
Academic Achievements
- "Norm-based Generalization Bounds for Sparse Neural Networks" (NeurIPS, 2023): Derived relatively tight generalization bounds for sparse neural networks (e.g., CNNs), highlighting the critical role of sparsity in generalization
- "Comparative Generalization Bounds for Deep Neural Networks" (TMLR, 2023): Introduced the concept of "effective depth," showing it is independent of actual depth and adapts to data complexity
- "On the Expressivity of Selective State-Space Layers: A Multivariate Polynomial Approach" (Under review, 2025): Demonstrated that selective state-space layers are more expressive than linear transformers
- "From Grounding to Planning: Benchmarking Bottlenecks in Web Agents with Mind2Web" (ECAI, 2025): Evaluated the relative importance of planning vs. grounding capabilities in natural language-based web tasks
- Recipient of the Francis Robbins Upton Fellowship
