arXiv research

Framework for fair classification with noisy protected attributes and provable guarantees.

PAC-Wrap provides provable guarantees for semi-supervised anomaly detection.

Paper develops robust neural network sensors for fuel injection quantities.

New neural methods for stable control with provable guarantees.

Topic models provide a useful method for dimensionality reduction and exploratory data analysis in large text corpora. Most approaches to topic model inference have been based on a maximum likelihood objective. Efficient algorithms exist that approximate this objective, but they have no provable guarantees. Recently, a…

In recent years several adversarial attacks and defenses have been proposed. Often seemingly robust models turn out to be non-robust when more sophisticated attacks are used. One way out of this dilemma are provable robustness guarantees. While provably robust models for specific $l_p$-perturbation models have been dev…

New method uses deep learning to solve inverse problems with provable guarantees.

Proposes efficient stochastic algorithms for optimizing NDCG with provable convergence guarantees.

Machine-learning models for security-critical applications such as bot, malware, or spam detection, operate in constrained discrete domains. These applications would benefit from having provable guarantees against adversarial examples. The existing literature on provable adversarial robustness of models, however, exclu…

We give two provably accurate feature-selection techniques for the linear SVM. The algorithms run in deterministic and randomized time respectively. Our algorithms can be used in an unsupervised or supervised setting. The supervised approach is based on sampling features from support vectors. We prove that the margin i…

Black-box variational inference tries to approximate a complex target distribution though a gradient-based optimization of the parameters of a simpler distribution. Provable convergence guarantees require structural properties of the objective. This paper shows that for location-scale family approximations, if the targ…

New framework for fair classification in adversarial settings with provable guarantees.

We solve ElasticNet regularization tuning across multiple instances with provable guarantees.

We study the problem of subspace tracking in the presence of missing data (ST-miss). In recent work, we studied a related problem called robust ST. In this work, we show that a simple modification of our robust ST solution also provably solves ST-miss and robust ST-miss. To our knowledge, our result is the first `compl…

New framework provides privacy guarantees for practical federated learning.

MPNN improves on UniFL approximation with provable guarantees.

New algorithm trains ReLU gates provably in linear time.

Novel algorithm accelerates PnP methods for image deblurring and super-resolution.

New AI error correctors improve classifier performance with provable guarantees.

Multi-model FL improves performance without sharing data.

New algorithm for weighted low rank approximation with provable guarantees.

Synthetic data can be used to ask more questions and accelerate discovery with provable validity guarantees.

A new clustering method improves recovery guarantees by re-embedding data.

RedEx improves neural network optimization with convex optimization guarantees.

Proves accuracy guarantees for self-supervised learning with correlated positive pairs.

PAC-Bayesian theory applied to learning optimization algorithms with generalization guarantees.

Paper analyzes InstaHide's security, recovering all private images with provable guarantee.

Study shows reinforcement learning algorithm's performance depends on metric space's size.

Training certifiable neural networks enables one to obtain models with robustness guarantees against adversarial attacks. In this work, we introduce a framework to bound the adversary-free region in the neighborhood of the input data by a polyhedral envelope, which yields finer-grained certified robustness. We further …

Efficient RL algorithm for multinomial logistic MDPs with provable guarantees.

Bayesian MAML outperforms MAML in meta learning tasks with theoretical guarantees.

New algorithm for online tensor factorization with provable guarantees.

Recent variational inference methods use stochastic gradient estimators whose variance is not well understood. Theoretical guarantees for these estimators are important to understand when these methods will or will not work. This paper gives bounds for the common "reparameterization" estimators when the target is smoot…

Extended analysis of Q-learning's efficiency, matching optimal regret.

Proposes MIP, a privacy notion that requires less randomness than DP, leading to better utility.

Paper tackles adaptive deletion of data points from trained models.

Proves efficient learning of hierarchical structure in meta-reinforcement learning.

In this paper, we propose a provably correct algorithm for convolutive nonnegative matrix factorization (CNMF) under separability assumptions. CNMF is a convolutive variant of nonnegative matrix factorization (NMF), which functions as an NMF with additional sequential structure. This model is useful in a number of appl…

Guarantees for third-person imitation learning from offline data.

A new principle and method improve out-of-distribution detection in generative models.

Non-negative matrix factorization (NMF) is a natural model of admixture and is widely used in science and engineering. A plethora of algorithms have been developed to tackle NMF, but due to the non-convex nature of the problem, there is little guarantee on how well these methods work. Recently a surge of research have …

Denoised smoothing defends pretrained classifiers against adversarial attacks.

Recently, there has been considerable progress on designing algorithms with provable guarantees -- typically using linear algebraic methods -- for parameter learning in latent variable models. But designing provable algorithms for inference has proven to be more challenging. Here we take a first step towards provable i…

Meta-learning control algorithm with finite-time guarantees for unknown systems.

Data-independent pruning method reduces neural network size with accuracy guarantees.

The paper tackles safe exploration in RL by a conservative safety critic.

Paper solves NP-hard sparse mixed linear regression problem with provable guarantees.

PARADE generates provably robust adversarial examples for deep networks.