Dhruva Karkada

~Dhruva_Karkada1

4

论文总数

2.0

年均投稿

7.0

平均评分

接收情况4/4

会议分布

NeurIPS

3

ICLR

1

发表论文 (4 篇)

20253 篇

Closed-Form Training Dynamics Reveal Learned Features and Linear Structure in Word2Vec-like Models

NeurIPS 2025Poster

On the Emergence of Linear Analogies in Word Embeddings

NeurIPS 2025Poster

Alternating Gradient Flows: A Theory of Feature Learning in Two-layer Neural Networks

NeurIPS 2025Poster

20241 篇

More is Better: when Infinite Overparameterization is Optimal and Overfitting is Obligatory

ICLR 2024Poster

合作者 (12)

James B Simon3 篇

Michael R DeWeese2 篇

Yasaman Bahri2 篇

Mikhail Belkin1 篇

Nikhil Ghosh1 篇

Daniel Kunin1 篇

Giovanni Luca Marchetti1 篇