activity
20212026
collaborators
Showing cs.LGShow all

6 papers · 1 filter

cs.LG2026

(How) Learning Rates Regulate Catastrophic Overtraining

Mark Rofin, Aditya Varre, Nicolas Flammarion

Supervised fine-tuning (SFT) is a common first stage of LLM post-training, teaching the model to follow instructions and shaping its behavior as a helpful assistant. At the same ti…

cs.LG2026

Gradient Flow Polarizes Softmax Outputs towards Low-Entropy Solutions

Aditya Varre, Mark Rofin, Nicolas Flammarion

Understanding the intricate non-convex training dynamics of softmax-based models is crucial for explaining the empirical success of transformers. In this article, we analyze the gr…

cs.LG2025

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

Aditya Varre, Gizem Yüce, Nicolas Flammarion

Motivated by empirical observations of prolonged plateaus and stage-wise progression during training, we investigate the loss landscape of transformer models trained on in-context…

cs.LG2023

Why Do We Need Weight Decay in Modern Deep Learning?

Francesco D'Angelo, Maksym Andriushchenko, Aditya Varre +1

Weight decay is a broadly used technique for training state-of-the-art deep networks from image classification to large language models. Despite its widespread usage and being exte…

cs.LG2022

Accelerated SGD for Non-Strongly-Convex Least Squares

Aditya Varre, Nicolas Flammarion

We consider stochastic approximation for the least squares regression problem in the non-strongly convex setting. We present the first practical algorithm that achieves the optimal…

cs.LG2021

Last iterate convergence of SGD for Least-Squares in the Interpolation regime

Aditya Varre, Loucas Pillaud-Vivien, Nicolas Flammarion

Motivated by the recent successes of neural networks that have the ability to fit the data perfectly and generalize well, we study the noiseless model in the fundamental least-squa…