α
Research
Alpha Leak
Conferences
Topics
Top Authors
Rankings
Browse All
EN
中
Home
/
Authors
/
Depen Morwani
Depen Morwani
5
papers
152
total citations
papers (5)
How Does Critical Batch Size Scale in Pre-training?
ICLR 2025
arXiv
43
citations
Deconstructing What Makes a Good Optimizer for Autoregressive Language Models
ICLR 2025
37
citations
A New Perspective on Shampoo's Preconditioner
ICLR 2025
arXiv
35
citations
Feature emergence via margin maximization: case studies in algebraic tasks
ICLR 2024
arXiv
30
citations
Beyond Implicit Bias: The Insignificance of SGD Noise in Online Learning
ICML 2024
arXiv
7
citations