research
∙
05/30/2023
How Does Information Bottleneck Help Deep Learning?
Numerous deep learning algorithms have been inspired by and understood v...
share
research
∙
04/08/2023
Last-Layer Fairness Fine-tuning is Simple and Effective for Neural Networks
As machine learning has been deployed ubiquitously across applications i...
research
∙
03/08/2023
HappyMap: A Generalized Multi-calibration Method
Multi-calibration is a powerful and evolving concept originating in the ...
research
∙
02/13/2023
Understanding Multimodal Contrastive Learning and Incorporating Unpaired Data
Language-supervised vision models have recently attracted great attentio...
research
∙
12/27/2022
Quantile Risk Control: A Flexible Framework for Bounding the Probability of High-Loss Predictions
Rigorous guarantees about the performance of predictive algorithms are n...
research
∙
11/08/2022
Reinforcement Learning with Stepwise Fairness Constraints
AI methods are used in societally important settings, ranging from credi...
research
∙
11/07/2022
Investigating Fairness Disparities in Peer Review: A Language Model Enhanced Approach
Double-blind peer review mechanism has become the skeleton of academic r...
research
∙
06/27/2022
Robustness Implies Generalization via Data-Dependent Generalization Bounds
This paper proves that robustness implies generalization via data-depend...
research
∙
06/06/2022
FIFA: Making Fairness More Generalizable in Classifiers Trained on Imbalanced Data
Algorithmic fairness plays an important role in machine learning and imp...
research
∙
11/04/2021
Scaffolding Sets
Predictors map individual instances in a population to the interval [0,1...
research
∙
10/06/2021
An Unconstrained Layer-Peeled Perspective on Neural Collapse
Neural collapse is a highly symmetric geometric pattern of neural networ...
research
∙
10/06/2021
The Power of Contrast for Feature Learning: A Theoretical Analysis
Contrastive learning has achieved state-of-the-art performance in variou...
research
∙
06/28/2021
Understanding Dynamics of Nonlinear Representation Learning and Its Application
Representations of the world environment play a crucial role in machine ...
research
∙
06/18/2021
Adversarial Training Helps Transfer Learning via Better Representations
Transfer learning aims to leverage models pre-trained on source data to ...
research
∙
02/11/2021
When and How Mixup Improves Calibration
In many machine learning applications, it is important for the model to ...
research
∙
10/27/2020
Toward Better Generalization Bounds with Locally Elastic Stability
Classical approaches in learning theory are often seen to yield very loo...
research
∙
10/20/2020
Towards Understanding the Dynamics of the First-Order Adversaries
An acknowledged weakness of neural networks is their vulnerability to ad...
research
∙
10/09/2020
How Does Mixup Help With Robustness and Generalization?
Mixup is a popular data augmentation technique based on taking convex co...
research
∙
10/03/2020
Interpreting Robust Optimization via Adversarial Influence Functions
Robust optimization has been widely used in nowadays data science, espec...
research
∙
09/26/2020
Decision-Aware Conditional GANs for Time Series Data
We introduce the decision-aware time-series conditional generative adver...
research
∙
06/20/2020
Representation via Representations: Domain Generalization via Adversarially Learned Invariant Representations
We investigate the power of censoring techniques, first developed for le...
research
∙
06/15/2020
Improving Adversarial Robustness via Unlabeled Out-of-Domain Data
Data augmentation by incorporating cheap unlabeled data from multiple do...
research
∙
06/04/2019