Search Results for author:
Found 32 papers, 17 papers with code
Atmospheric Transport Modeling of CO$_2$ with Neural Networks
Accurately describing the distribution of CO$_2$ in the atmosphere with atmospheric tracer transport models is essential for greenhouse gas monitoring and verification support systems to aid implementation of international climate agreements.
Strong Copyright Protection for Language Models via Adaptive Model Fusion
The risk of language models unintentionally reproducing copyrighted material from their training data has led to the development of various protective measures.
Robust Mixture Learning when Outliers Overwhelm Small Groups
We study the problem of estimating the means of well-separated mixtures when an adversary may add arbitrary outliers.
Detecting critical treatment effect bias in small subgroups
Randomized trials are considered the gold standard for making informed decisions in medicine, yet they often lack generalizability to the patient populations in clinical practice.
Privacy-preserving data release leveraging optimal transport and particle gradient descent
We present a novel approach for differentially private data synthesis of protected tabular datasets, a relevant task in highly sensitive domains such as healthcare and government.
Hidden yet quantifiable: A lower bound for confounding strength using randomized trials
Further, we show how our lower bound can correctly identify the absence and presence of unobserved confounding in a real-world setting.
Can semi-supervised learning use all the data effectively? A lower bound perspective
Prior works have shown that semi-supervised learning algorithms can leverage unlabeled data to improve over the labeled sample complexity of supervised learning (SL) algorithms.
How robust accuracy suffers from certified training with convex relaxations
In this paper, we systematically compare the standard and robust error of these two robust training paradigms across multiple computer vision tasks.
PILLAR: How to make semi-private learning more effective
In Semi-Supervised Semi-Private (SP) learning, the learner has access to both public unlabelled and private labelled data.
Strong inductive biases provably prevent harmless interpolation
Classical wisdom suggests that estimators should avoid fitting noise to achieve good generalization.
Tight bounds for maximum $\ell_1$-margin classifiers
In particular, for the noiseless setting, we prove tight upper and lower bounds for the prediction error that match existing rates of order $\frac{\|w^*\|_1^{2/3}}{n^{1/3}}$ for general ground truths.
Margin-based sampling in high dimensions: When being active is less efficient than staying passive
It is widely believed that given the same labeling budget, active learning (AL) algorithms like margin-based active learning achieve better predictive performance than passive learning (PL), albeit at a higher computational cost.
How unfair is private learning ?
As machine learning algorithms are deployed on sensitive data in critical decision making processes, it is becoming increasingly important that they are also private and fair.
Provable concept learning for interpretable predictions using variational autoencoders
In safety-critical applications, practitioners are reluctant to trust neural networks when no interpretable explanations are available.
Fast Rates for Noisy Interpolation Require Rethinking the Effects of Inductive Bias
Good generalization performance on high-dimensional data crucially hinges on a simple structure of the ground truth and a corresponding strong inductive bias of the estimator.
Why adversarial training can hurt robust accuracy
Machine learning classifiers with high test accuracy often perform poorly under adversarial attacks.
Tight bounds for minimum l1-norm interpolation of noisy data
We provide matching upper and lower bounds of order $\sigma^2/\log(d/n)$ for the prediction error of the minimum $\ell_1$-norm interpolator, a. k. a.
Self-supervised Reinforcement Learning with Independently Controllable Subgoals
We propose a novel self-supervised agent that estimates relations between environment components and uses them to independently control different parts of the environment state.
Interpolation can hurt robust generalization even when there is no noise
Numerous recent works show that overparameterization implicitly reduces variance for min-norm interpolators and max-margin classifiers.
Maximizing the robust margin provably overfits on noiseless data
Numerous recent works show that overparameterization implicitly reduces variance, suggesting vanishing benefits for explicit regularization in high dimensions.
How rotational invariance of common kernels prevents generalization in high dimensions
Kernel ridge regression is well-known to achieve minimax optimal rates in low-dimensional settings.
Semi-supervised novelty detection using ensembles with regularized disagreement
Deep neural networks often predict samples with high confidence even when they come from unseen classes and should instead be flagged for expert evaluation.
Ranked #1 on
Out-of-Distribution Detection
on CIFAR-10 vs CIFAR-10.1
(using extra training data)
Learn what you can't learn: Regularized Ensembles for Transductive out-of-distribution detection
This paper studies how such ``hard'' OOD scenarios can benefit from tuning the detection method after observing a batch of the test data.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
Understanding and Mitigating the Tradeoff Between Robustness and Accuracy
In this work, we precisely characterize the effect of augmentation on the standard error in linear regression when the optimal linear predictor has zero standard and robust error.
When Covariate-shifted Data Augmentation Increases Test Error And How to Fix It
Empirically, data augmentation sometimes improves and sometimes hurts test error, even when only adding points with labels from the true conditional distribution that the hypothesis class is expressive enough to fit.
Invariance-inducing regularization using worst-case transformations suffices to boost accuracy and spatial robustness
This work provides theoretical and empirical evidence that invariance-inducing regularizers can increase predictive accuracy for worst-case spatial transformations (spatial robustness).
Adversarial Training Can Hurt Generalization
While adversarial training can improve robust accuracy (against an adversary), it sometimes hurts standard accuracy (when there is no adversary).
Regularized Learning for Domain Adaptation under Label Shifts
We derive a generalization bound for the classifier on the target domain which is independent of the (ambient) data dimensions, and instead only depends on the complexity of the function class.
Online control of the false discovery rate with decaying memory
In the online multiple testing problem, p-values corresponding to different null hypotheses are observed one by one, and the decision of whether or not to reject the current hypothesis must be made immediately, after which the next p-value is observed.
Early stopping for kernel boosting algorithms: A general analysis with localized complexities
Early stopping of iterative algorithms is a widely-used form of regularization in statistics, commonly used in conjunction with boosting and related gradient-type algorithms.
A framework for Multi-A(rmed)/B(andit) testing with online FDR control
We propose an alternative framework to existing setups for controlling false alarms when multiple A/B tests are run over time.
Statistical and Computational Guarantees for the Baum-Welch Algorithm
By exploiting this characterization, we provide non-asymptotic finite sample guarantees on the Baum-Welch updates, guaranteeing geometric convergence to a small ball of radius on the order of the minimax rate around a global optimum.
