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
∙
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
∙
01/18/2023
Strong inductive biases provably prevent harmless interpolation
Classical wisdom suggests that estimators should avoid fitting noise to ...
research
∙
12/07/2022
Tight bounds for maximum ℓ_1-margin classifiers
Popular iterative algorithms such as boosting methods and coordinate des...
research
∙
12/01/2022
Uniform versus uncertainty sampling: When being active is less efficient than staying passive
It is widely believed that given the same labeling budget, active learni...
research
∙
06/08/2022
How unfair is private learning ?
As machine learning algorithms are deployed on sensitive data in critica...
research
∙
04/01/2022
Provable concept learning for interpretable predictions using variational inference
In safety critical applications, practitioners are reluctant to trust ne...
research
∙
03/07/2022
Fast rates for noisy interpolation require rethinking the effects of inductive bias
Good generalization performance on high-dimensional data crucially hinge...
research
∙
03/03/2022
Why adversarial training can hurt robust accuracy
Machine learning classifiers with high test accuracy often perform poorl...
research
∙
11/10/2021
Tight bounds for minimum l1-norm interpolation of noisy data
We provide matching upper and lower bounds of order σ^2/log(d/n) for the...
research
∙
09/09/2021
Self-supervised Reinforcement Learning with Independently Controllable Subgoals
To successfully tackle challenging manipulation tasks, autonomous agents...
research
∙
08/05/2021
Interpolation can hurt robust generalization even when there is no noise
Numerous recent works show that overparameterization implicitly reduces ...
research
∙
04/09/2021
How rotational invariance of common kernels prevents generalization in high dimensions
Kernel ridge regression is well-known to achieve minimax optimal rates i...
research
∙
12/10/2020
Learn what you can't learn: Regularized Ensembles for Transductive Out-of-distribution Detection
Machine learning models are often used in practice if they achieve good ...
research
∙
02/25/2020
Understanding and Mitigating the Tradeoff Between Robustness and Accuracy
Adversarial training augments the training set with perturbations to imp...
research
∙
06/26/2019
Invariance-inducing regularization using worst-case transformations suffices to boost accuracy and spatial robustness
This work provides theoretical and empirical evidence that invariance-in...
research
∙
06/14/2019
Adversarial Training Can Hurt Generalization
While adversarial training can improve robust accuracy (against an adver...
research
∙
03/22/2019
Regularized Learning for Domain Adaptation under Label Shifts
We propose Regularized Learning under Label shifts (RLLS), a principled ...
research
∙
10/02/2017
Online control of the false discovery rate with decaying memory
In the online multiple testing problem, p-values corresponding to differ...
research
∙
07/05/2017
Early stopping for kernel boosting algorithms: A general analysis with localized complexities
Early stopping of iterative algorithms is a widely-used form of regulari...
research
∙
06/16/2017
A framework for Multi-A(rmed)/B(andit) testing with online FDR control
We propose an alternative framework to existing setups for controlling f...
research
∙
12/27/2015