research
∙
06/12/2023
How robust accuracy suffers from certified training with convex relaxations
Adversarial attacks pose significant threats to deploying state-of-the-a...
share
research
∙
06/06/2023
PILLAR: How to make semi-private learning more effective
In Semi-Supervised Semi-Private (SP) learning, the learner has access to...
research
∙
04/25/2023
Certifying Ensembles: A General Certification Theory with S-Lipschitzness
Improving and guaranteeing the robustness of deep learning models has be...
research
∙
02/19/2023
Sample-efficient private data release for Lipschitz functions under sparsity assumptions
Differential privacy is the de facto standard for protecting privacy in ...
research
∙
10/10/2022
Do you pay for Privacy in Online learning?
Online learning, in the mistake bound model, is one of the most fundamen...
research
∙
07/08/2022
A law of adversarial risk, interpolation, and label noise
In supervised learning, it has been shown that label noise in the data c...
research
∙
06/17/2022
How robust are pre-trained models to distribution shift?
The vulnerability of machine learning models to spurious correlations ha...
research
∙
06/16/2022
Catastrophic overfitting is a bug but also a feature
Despite clear computational advantages in building robust neural network...
research
∙
06/08/2022
How unfair is private learning ?
As machine learning algorithms are deployed on sensitive data in critica...
research
∙
02/02/2022
Make Some Noise: Reliable and Efficient Single-Step Adversarial Training
Recently, Wong et al. showed that adversarial training with single-step ...
research
∙
08/16/2021
Identifying and Exploiting Structures for Reliable Deep Learning
Deep learning research has recently witnessed an impressively fast-paced...
research
∙
07/08/2020
How benign is benign overfitting?
We investigate two causes for adversarial vulnerability in deep neural n...
research
∙
06/16/2020
Progressive Skeletonization: Trimming more fat from a network at initialization
Recent studies have shown that skeletonization (pruning parameters) of n...
research
∙
02/21/2020
Calibrating Deep Neural Networks using Focal Loss
Miscalibration – a mismatch between a model's confidence and its correct...
research
∙
06/11/2019
Stable Rank Normalization for Improved Generalization in Neural Networks and GANs
Exciting new work on the generalization bounds for neural networks (NN) ...
research
∙
06/09/2018
TAPAS: Tricks to Accelerate (encrypted) Prediction As a Service
Machine learning methods are widely used for a variety of prediction pro...
research
∙
04/19/2018
Low Rank Structure of Learned Representations
A key feature of neural networks, particularly deep convolutional neural...
research
∙
01/31/2018
Optimizing Non-decomposable Measures with Deep Networks
We present a class of algorithms capable of directly training deep neura...
research
∙
07/05/2017
Agent based simulation of the evolution of society as an alternate maximization problem
Understanding the evolution of human society, as a complex adaptive syst...
research
∙
07/03/2017