Aditya Varre

~Aditya_Varre1

4

论文总数

2.0

年均投稿

5.8

平均评分

接收情况3/4

会议分布

NeurIPS

2

ICML

1

ICLR

1

发表论文 (4 篇)

20251 篇

Learning In-context $n$-grams with Transformers: Sub-$n$-grams Are Near-Stationary Points

ICML 2025Poster

20243 篇

SGD vs GD: Rank Deficiency in Linear Networks

NeurIPS 2024Poster

Why Do We Need Weight Decay in Modern Deep Learning?

NeurIPS 2024Poster

Why Do We Need Weight Decay in Modern Deep Learning?

ICLR 2024withdrawn

合作者 (5)

Nicolas Flammarion4 篇

Francesco D'Angelo2 篇

Maksym Andriushchenko2 篇

Gizem Yüce1 篇

Margarita Sagitova1 篇