← Authors

Mor Shpigel Nacson

12 papers · 2018–2025 · 5 conferences · across top CS/AI conferences

Achievements

πŸ—ΊοΈ Taxonomy Completionist (12) 🌍 Conference Polyglot (5) πŸƒ Academic Marathon (7) 🐣 Hot Topic Early Bird 🐝 Cross-Pollinator (10) πŸŒ‰ Interdisciplinary Bridge 🧭 Keyword Pioneer 🀝 Dynamic Duo (11) ❓ The Questioner πŸš€ Conference Pioneer πŸ’Ž Century Club (12) πŸ”₯ Unstoppable (8)

Conferences

ICML (5) ICLR (3) AISTATS (2) CVPR (1) JMLR (1)

Top co-authors

Daniel Soudry (11) Nathan Srebro (8) Elad Hoffer (3) Suriya Gunasekar (3) Jason Lee (2) Amir Globerson (1) Yair Carmon (1) Itamar Harel (1) Edward Moroshko (1) Shahar Azulay (1)

Keywords

gradient descent (6) separable datum (3) implicit bia (3) gradient flow (2) convergence rate (2) logistic loss (2) neural network optimization (1) loss landscape (1) sparse regression (1) margin maximization (1) maximum margin (1) linear classifier (1) inductive bia (1) implicit regularization (1) linear network (1) vision-language model (1) edge of stability (1) optical character recognition (1) token reduction (1) diagonal network (1)

Papers

DocVLM: Make Your VLM an Efficient Reader CVPR 2025
How Uniform Random Weights Induce Non-uniform Bias: Typical Interpolating Neural Networks Generalize with Narrow Teachers ICML 2024
Gradient Descent Monotonically Decreases the Sharpness of Gradient Flow Solutions in Scalar Networks and Beyond ICML 2023
The Implicit Bias of Minima Stability in Multivariate Shallow ReLU Networks ICLR 2023
Implicit Bias of the Step Size in Linear Diagonal Neural Networks ICML 2022
On the Implicit Bias of Initialization Shape: Beyond Infinitesimal Mirror Descent ICML 2021
At Stability's Edge: How to Adjust Hyperparameters to Preserve Minima Selection in Asynchronous Training of Neural Networks? ICLR 2020
Stochastic Gradient Descent on Separable Data: Exact Convergence with a Fixed Learning Rate AISTATS 2019
Convergence of Gradient Descent on Separable Data AISTATS 2019
Lexicographic and Depth-Sensitive Margins in Homogeneous and Non-Homogeneous Deep Models ICML 2019
The Implicit Bias of Gradient Descent on Separable Data ICLR 2018
The Implicit Bias of Gradient Descent on Separable Data JMLR 2018