4 citations · 15 across the 10 of their papers we have counts for
6 papers · 1 filter
How Do Transformers Learn Topic Structure: Towards a Mechanistic Understanding
Yuchen Li, Yuanzhi Li, Andrej Risteski
While the successes of transformers across many domains are indisputable, accurate understanding of the learning mechanics is still largely lacking. Their capabilities have been pr…
Contrasting the landscape of contrastive and non-contrastive learning
Ashwini Pokle, Jinjin Tian, Yuchen Li +1
A lot of recent advances in unsupervised feature learning are based on designing features which are invariant under semantic data augmentations. A common way to do this is contrast…
Improving greedy core-set configurations for active learning with uncertainty-scaled distances
Yuchen Li, Frank Rudzicz
We scale perceived distances of the core-set algorithm by a factor of uncertainty and search for low-confidence configurations, finding significant improvements in sample efficienc…
Privacy Threats Analysis to Secure Federated Learning
Yuchen Li, Yifan Bao, Liyao Xiang +4
Federated learning is emerging as a machine learning technique that trains a model across multiple decentralized parties. It is renowned for preserving privacy as the data never le…
Variations on the Chebyshev-Lagrange Activation Function
Yuchen Li, Frank Rudzicz, Jekaterina Novikova
We seek to improve the data efficiency of neural networks and present novel implementations of parameterized piece-wise polynomial activation functions. The parameters are the y-co…
ChainGAN: A sequential approach to GANs
Safwan Hossain, Kiarash Jamali, Yuchen Li +1
We propose a new architecture and training methodology for generative adversarial networks. Current approaches attempt to learn the transformation from a noise sample to a generate…