29 citations · 158 across the 26 of their papers we have counts for
6 papers · 1 filter
Scaffolding Sets
Maya Burhanpurkar, Zhun Deng, Cynthia Dwork +1
Predictors map individual instances in a population to the interval . For a collection of subsets of a population, a predictor is multi-calibrated with respect…
An Unconstrained Layer-Peeled Perspective on Neural Collapse
Wenlong Ji, Yiping Lu, Yiliang Zhang +2
Neural collapse is a highly symmetric geometric pattern of neural networks that emerges during the terminal phase of training, with profound implications on the generalization perf…
The Power of Contrast for Feature Learning: A Theoretical Analysis
Wenlong Ji, Zhun Deng, Ryumei Nakada +2
Contrastive learning has achieved state-of-the-art performance in various self-supervised learning tasks and even outperforms its supervised counterpart. Despite its empirical succ…
Adversarial Training Helps Transfer Learning via Better Representations
Zhun Deng, Linjun Zhang, Kailas Vodrahalli +2
Transfer learning aims to leverage models pre-trained on source data to efficiently adapt to target setting, where only limited data are available for model fine-tuning. Recent wor…
Understanding Dynamics of Nonlinear Representation Learning and Its Application
Kenji Kawaguchi, Linjun Zhang, Zhun Deng
Representations of the world environment play a crucial role in artificial intelligence. It is often inefficient to conduct reasoning and inference directly in the space of raw sen…
When and How Mixup Improves Calibration
Linjun Zhang, Zhun Deng, Kenji Kawaguchi +1
In many machine learning applications, it is important for the model to provide confidence scores that accurately capture its prediction uncertainty. Although modern learning metho…