Depen Morwani
9 papers · 2022–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
🌍
Conference Polyglot
(4)
🌉
Interdisciplinary Bridge
🧭
Keyword Pioneer
🐝
Cross-Pollinator
(15)
❓
The Questioner
Conferences
ICLR (5)
NIPS (2)
ALT (1)
ICML (1)
Top co-authors
Keywords
neural network
(2)
feature learning
(1)
neural network optimization
(1)
gradient descent
(1)
sparse solution
(1)
ensemble method
(1)
inductive bia
(1)
simplicity bia
(1)
infinite width
(1)
infinite width limit
(1)
finite width analysis
(1)
representation learning
(1)
exponential weight normalization
(1)
Papers
SOAP: Improving and Stabilizing Shampoo using Adam for Language Modeling
ICLR 2025
Deconstructing What Makes a Good Optimizer for Autoregressive Language Models
ICLR 2025
How Does Critical Batch Size Scale in Pre-training?
ICLR 2025
A New Perspective on Shampoo's Preconditioner
ICLR 2025
Beyond Implicit Bias: The Insignificance of SGD Noise in Online Learning
ICML 2024
Feature emergence via margin maximization: case studies in algebraic tasks
ICLR 2024
Simplicity Bias in 1-Hidden Layer Neural Networks
NIPS 2023
Feature-Learning Networks Are Consistent Across Widths At Realistic Scales
NIPS 2023
Inductive Bias of Gradient Descent for Weight Normalized Smooth Homogeneous Neural Nets
ALT 2022