4 citations · 6 across the 6 of their papers we have counts for
7 papers
Solving adversarial examples requires solving exponential misalignment
Alessandro Salvatore, Stanislav Fort, Surya Ganguli
Adversarial attacks - input perturbations imperceptible to humans that fool neural networks - remain both a persistent failure mode in machine learning, and a phenomenon with myste…
Alternating Gradient Flows: A Theory of Feature Learning in Two-layer Neural Networks
Daniel Kunin, Giovanni Luca Marchetti, Feng Chen +5
What features neural networks learn, and how, remains an open question. In this paper, we introduce Alternating Gradient Flows (AGF), an algorithmic framework that describes the dy…
Rethinking Fine-Tuning when Scaling Test-Time Compute: Limiting Confidence Improves Mathematical Reasoning
Feng Chen, Allan Raventos, Nan Cheng +2
Recent progress in large language models (LLMs) highlights the power of scaling test-time compute to achieve strong performance on complex tasks, such as mathematical reasoning and…
An analytic theory of creativity in convolutional diffusion models
Mason Kamb, Surya Ganguli
We obtain an analytic, interpretable and predictive theory of creativity in convolutional diffusion models. Indeed, score-matching diffusion models can generate highly original ima…
Features are fate: a theory of transfer learning in high-dimensional regression
Javan Tahir, Surya Ganguli, Grant M. Rotskoff
With the emergence of large-scale pre-trained neural networks, methods to adapt such "foundation" models to data-limited downstream tasks have become a necessity. Fine-tuning, pref…
Get rich quick: exact solutions reveal how unbalanced initializations promote rapid feature learning
Daniel Kunin, Allan Raventós, Clémentine Dominé +4
While the impressive performance of modern neural networks is often attributed to their capacity to efficiently extract task-relevant features from data, the mechanisms underlying…
Geometric Dynamics of Signal Propagation Predict Trainability of Transformers
Aditya Cowsik, Tamra Nebabu, Xiao-Liang Qi +1
We investigate forward signal propagation and gradient back propagation in deep, randomly initialized transformers, yielding simple necessary and sufficient conditions on initializ…