arXiv research

A scheme robust to action erasures improves MAB performance.

New lower bounds show sparse recovery is hard even with multiple preconditioners.

New study shows feedback doesn't improve MAB performance over erasure channels.

TaCo prevents non-linear classifiers from detecting sensitive attributes.

This paper considers the recovery of a low-rank matrix from an observed version that simultaneously contains both (a) erasures: most entries are not observed, and (b) errors: values at a constant fraction of (unknown) locations are arbitrarily corrupted. We provide a new unified performance guarantee on when the natura…

We consider the problem of clustering a set of high-dimensional data points into sets of low-dimensional linear subspaces. The number of subspaces, their dimensions, and their orientations are unknown. We propose a simple and low-complexity clustering algorithm based on thresholding the correlations between the data po…

Differentiable Masking reveals how neural models make decisions across layers.

Paper proposes SSSE, an efficient method to erase samples from trained models.

Residual Networks with convolutional layers are widely used in the field of machine learning. Since they effectively extract features from input data by stacking multiple layers, they can achieve high accuracy in many applications. However, the stacking of many layers raises their computation costs. To address this pro…

This paper considers the problem of implementing large-scale gradient descent algorithms in a distributed computing setting in the presence of {\em straggling} processors. To mitigate the effect of the stragglers, it has been previously proposed to encode the data with an erasure-correcting code and decode at the maste…

A new iterative low complexity algorithm has been presented for computing the Walsh-Hadamard transform (WHT) of an $N$ dimensional signal with a $K$-sparse WHT, where $N$ is a power of two and $K = O(N^α)$, scales sub-linearly in $N$ for some $0 < α< 1$. Assuming a random support model for the non-zero transform domain…

We prove several results about chordal graphs and weighted chordal graphs by focusing on exposed edges. These are edges that are properly contained in a single maximal complete subgraph. This leads to a characterization of chordal graphs via deletions of a sequence of exposed edges from a complete graph. Most interesti…

COCA refactors training data to identify and erase unsafe concepts in LLMs.

We consider high dimensional sparse regression, and develop strategies able to deal with arbitrary -- possibly, severe or coordinated -- errors in the covariance matrix $X$. These may come from corrupted data, persistent experimental errors, or malicious respondents in surveys/recommender systems, etc. Such non-stochas…

Formula derived for sample complexity in binary hypothesis testing.

Introduces MPR to measure and optimize representation across intersectional groups in retrieval.

CSD learns a common component for domain generalization, outperforming existing methods.

In this paper, we model Density Evolution (DE) using Recurrent Neural Networks (RNNs) with the aim of designing capacity-approaching Irregular Low-Density Parity-Check (LDPC) codes for binary erasure channels. In particular, we present a method for determining the coefficients of the degree distributions, characterizin…

Performance of distributed optimization and learning systems is bottlenecked by "straggler" nodes and slow communication links, which significantly delay computation. We propose a distributed optimization framework where the dataset is "encoded" to have an over-complete representation with built-in redundancy, and the …

No universal trading strategy exists due to mathematical impossibilities.

We describe the Fast Greedy Sparse Subspace Clustering (FGSSC) algorithm providing an efficient method for clustering data belonging to a few low-dimensional linear or affine subspaces. The main difference of our algorithm from predecessors is its ability to work with noisy data having a high rate of erasures (missed e…

We study "active" decision making over sensor networks where the sensors' sequential probing actions are actively chosen by continuously learning from past observations. We consider two network settings: with and without central coordination. In the first case, the network nodes interact with each other through a centr…

Data ownership and data protection are increasingly important topics with ethical and legal implications, e.g., with the right to erasure established in the European General Data Protection Regulation (GDPR). In this light, we investigate network embeddings, i.e., the representation of network nodes as low-dimensional …

The emergence of various intelligent mobile applications demands the deployment of powerful deep learning models at resource-constrained mobile devices. The device-edge co-inference framework provides a promising solution by splitting a neural network at a mobile device and an edge computing server. In order to balance…

We propose a framework for verifying data deletion in MLaaS systems.

Boosts barely robust learners to be more adversarially robust.

AAT separates robust and non-robust features without supervision.

Neural Networks have been shown to be sensitive to common perturbations such as blur, Gaussian noise, rotations, etc. They are also vulnerable to some artificial malicious corruptions called adversarial examples. The adversarial examples study has recently become very popular and it sometimes even reduces the term "adv…

New research shows flat minima in robust loss landscapes correlate with good adversarial robustness.

Voting ensemble of robust models improves robustness.

Study privacy and robustness in learning halfspaces, proving hard trade-offs.

We introduce a new metric to evaluate corruption robustness of ML classifiers.

Robust learning method combines kernel smoothing and robust optimization.

Study shows how bias in optimization affects robustness in adversarial settings.

ClusTR improves clustering-based models' robustness without adversarial training.

SCORE resolves the robustness vs accuracy trade-off by redefining robust error.

Develops robust learning framework under distributional perturbations.

The study examines robust decision-making in volatile financial markets, finding action robustness is more impactful than uncertainty tolerance.

Making neural networks robust against adversarial inputs has resulted in an arms race between new defenses and attacks. The most promising defenses, adversarially robust training and verifiably robust training, have limitations that restrict their practical applications. The adversarially robust training only makes the…

Proposes a new method for nonlinear models with robustness guarantees.

This work introduces new ways to compare adversarial robustness of classifiers globally.

Batch normalization shifts models to rely more on non-robust features.

Paper develops a robust Bayesian optimization method for noisy zeroth-order settings.

Paper proposes robust generative models using VAEs.

Paper proposes a robust metric learning algorithm.

HYDRA prunes robust neural networks to improve both benign and adversarial robustness.

Study improves image classifier robustness to random p-norm corruptions.

The paper assesses machine learning robustness with covariate perturbations.