Aditya Varre

PhD student, EPFL - EPF Lausanne

Joined

May 2021

Names

Aditya Varre (Preferred)

Aditya Vardhan Varre

Emails

****@epfl.ch (Confirmed)

Personal Links

DBLP

Career & Education History

PhD student

EPFL - EPF Lausanne (epfl.ch)

2021 – Present

MS student

Swiss Federal Institute of Technology Lausanne (epfl.ch)

2019 – 2021

Undergrad student

Indian Institute of Technology Bombay, Indian Institute of Technology Bombay (cse.iitb.ac.in)

2014 – 2018

Advisors, Relations & Conflicts

No relations added

Expertise

No areas of expertise listed

Publications

Incremental Learning in Transformers for In-Context Associative Recall
Aditya Varre, Nicolas Flammarion
- EurIPS 2025 Workshop PriGM
- Readers: Everyone
Incremental Learning in Transformers for In-Context Associative Recall
Aditya Varre, Nicolas Flammarion
- Submitted to ICLR 2026
- Readers: Everyone
Learning In-context $n$-grams with Transformers: Sub-$n$-grams Are Near-Stationary Points
Aditya Varre, Gizem Yüce, Nicolas Flammarion
- ICML 2025 poster
- Readers: Everyone
SGD vs GD: Rank Deficiency in Linear Networks
Aditya Varre, Margarita Sagitova, Nicolas Flammarion
- HiLD at ICML 2024 Poster
- Readers: Everyone
SGD vs GD: Rank Deficiency in Linear Networks
Aditya Varre, Margarita Sagitova, Nicolas Flammarion
- NeurIPS 2024 poster
- Readers: Everyone
Why Do We Need Weight Decay in Modern Deep Learning?
Francesco D'Angelo, Maksym Andriushchenko, Aditya Varre, Nicolas Flammarion
- NeurIPS 2024 poster
- Readers: Everyone
Why Do We Need Weight Decay for Overparameterized Deep Networks?
Francesco D'Angelo, Aditya Varre, Maksym Andriushchenko, Nicolas Flammarion
- M3L 2023 Poster
- Readers: Everyone
Why Do We Need Weight Decay in Modern Deep Learning?
Maksym Andriushchenko, Francesco D'Angelo, Aditya Varre, Nicolas Flammarion
- ICLR 2024 Conference Withdrawn Submission
- Readers: Everyone
On the spectral bias of two-layer linear networks
Aditya Vardhan Varre, Maria-Luiza Vladarean, Loucas Pillaud-Vivien, Nicolas Flammarion
- NeurIPS 2023 poster
- Readers: Everyone
SGD with Large Step Sizes Learns Sparse Features
Maksym Andriushchenko, Aditya Vardhan Varre, Loucas Pillaud-Vivien, Nicolas Flammarion
- ICML 2023 Poster
- Readers: Everyone

View all 17 publications