3 citations · 8 across the 9 of their papers we have counts for
9 papers
Beyond Red-Teaming: Formal Guarantees of LLM Guardrail Classifiers
Nikita Kezins, Urbas Ekka, Pascal Berrang +1
Guardrail Classifiers defend production language models against harmful behavior, but although results seem promising in testing, they provide no formal guarantees. Providing forma…
Deep Learning as Neural Low-Degree Filtering: A Spectral Theory of Hierarchical Feature Learning
Yatin Dandi, Matteo Vilucchio, Luca Arnaboldi +2
Understanding how deep neural networks learn useful internal representations from data remains a central open problem in the theory of deep learning. We introduce Neural Low-Degree…
ColBERT-Zero: To Pre-train Or Not To Pre-train ColBERT models
Antoine Chaffin, Luca Arnaboldi, Amélie Chatelain +1
Current state-of-the-art multi-vector models are obtained through a small Knowledge Distillation (KD) training step on top of strong single-vector models, leveraging the large-scal…
Asymptotics of SGD in Sequence-Single Index Models and Single-Layer Attention Networks
Luca Arnaboldi, Bruno Loureiro, Ludovic Stephan +2
We study the dynamics of stochastic gradient descent (SGD) for a class of sequence models termed Sequence Single-Index (SSI) models, where the target depends on a single direction…
Online Learning and Information Exponents: On The Importance of Batch size, and Time/Complexity Tradeoffs
Luca Arnaboldi, Yatin Dandi, Florent Krzakala +3
We study the impact of the batch size on the iteration time of training two-layer neural networks with one-pass stochastic gradient descent (SGD) on multi-index target fu…
Repetita Iuvant: Data Repetition Allows SGD to Learn High-Dimensional Multi-Index Functions
Luca Arnaboldi, Yatin Dandi, Florent Krzakala +2
Neural networks can identify low-dimensional relevant structures within high-dimensional noisy data, yet our mathematical understanding of how they do so remains scarce. Here, we i…
The Benefits of Reusing Batches for Gradient Descent in Two-Layer Networks: Breaking the Curse of Information and Leap Exponents
Yatin Dandi, Emanuele Troiani, Luca Arnaboldi +3
We investigate the training dynamics of two-layer neural networks when learning multi-index target functions. We focus on multi-pass gradient descent (GD) that reuses the batches m…
Escaping mediocrity: how two-layer networks learn hard generalized linear models with SGD
Luca Arnaboldi, Florent Krzakala, Bruno Loureiro +1
This study explores the sample complexity for two-layer neural networks to learn a generalized linear target function under Stochastic Gradient Descent (SGD), focusing on the chall…
From high-dimensional & mean-field dynamics to dimensionless ODEs: A unifying approach to SGD in two-layers networks
Luca Arnaboldi, Ludovic Stephan, Florent Krzakala +1
This manuscript investigates the one-pass stochastic gradient descent (SGD) dynamics of a two-layer neural network trained on Gaussian data and labels generated by a similar, thoug…