research
∙
07/24/2023
On Privileged and Convergent Bases in Neural Network Representations
In this study, we investigate whether the representations learned by neu...
share
research
∙
02/02/2023
The unreasonable effectiveness of few-shot learning for machine translation
We demonstrate the potential of few-shot translation systems, trained wi...
research
∙
06/20/2022
Limitations of the NTK for Understanding Generalization in Deep Learning
The “Neural Tangent Kernel” (NTK) (Jacot et al 2018), and its empirical ...
research
∙
02/04/2022
Data Scaling Laws in NMT: The Effect of Noise and Architecture
In this work, we study the effect of varying the architecture and traini...
research
∙
06/14/2021
Revisiting Model Stitching to Compare Neural Representations
We revisit and extend model stitching (Lenc Vedaldi 2015) as a metho...
research
∙
10/25/2020
Improving the Reconstruction of Disentangled Representation Learners via Multi-Stage Modelling
Current autoencoder-based disentangled representation learning methods a...
research
∙
10/16/2020
For self-supervised learning, Rationality implies generalization, provably
We prove a new upper bound on the generalization gap of classifiers that...
research
∙
09/17/2020
Distributional Generalization: A New Kind of Generalization
We introduce a new notion of generalization – Distributional Generalizat...
research
∙
12/04/2019
Deep Double Descent: Where Bigger Models and More Data Hurt
We show that a variety of modern deep learning tasks exhibit a "double-d...
research
∙
06/03/2018
Minnorm training: an algorithm for training over-parameterized deep neural networks
In this work, we propose a new training method for finding minimum weigh...
research
∙
06/03/2018