arXiv research

TaCo prevents non-linear classifiers from detecting sensitive attributes.

A scheme robust to action erasures improves MAB performance.

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

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…

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

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

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…

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…

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

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…

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…

ECBMs unify concept-based interpretations in deep learning models.

MCD offers a complete model understanding for high-stake decisions.

Concept-driven OPE reduces variance in off-policy decision evaluation.

DCR improves interpretability of concept-based models by using neural networks to build rule structures.

Concept bottleneck models enable concept manipulation for model interpretation.

This review covers learning under concept drift, including detection, understanding, and adaptation.

New method discovers concepts in hidden feature layers using sparse subspace clustering.

Proposes a simple method to represent and manipulate concepts using polynomials and moment statistics.

Geometric framework detects concept frustration between human concepts and machine representations.

Human explanations of high-level decisions are often expressed in terms of key concepts the decisions are based on. In this paper, we study such concept-based explainability for Deep Neural Networks (DNNs). First, we define the notion of completeness, which quantifies how sufficient a particular set of concepts is in e…

The study identifies latent concepts from diverse observations without assuming specific models.

LCBM model improves image classification without human supervision.

New models handle survival analysis with concept-based learning.

New methods identify concepts in trained embeddings reliably without human labels.

CREAM models enable concept-grounded predictions and interpretability.

Generative concept representations have three major advantages over discriminative ones: they can represent uncertainty, they support integration of learning and reasoning, and they are good for unsupervised and semi-supervised learning. We discuss probabilistic and generative deep learning, which generative concept re…

New framework quantifies and reduces concept-based models' leakage.

Formula derived for sample complexity in binary hypothesis testing.

PCBMs turn any neural network into interpretable models without dense annotations.

In an attempt to gather a deeper understanding of how convolutional neural networks (CNNs) reason about human-understandable concepts, we present a method to infer labeled concept data from hidden layer activations and interpret the concepts through a shallow decision tree. The decision tree can provide information abo…

Framework learns interpretable concepts from data without interventions.

A new framework forecasts stock trends by mining shared information from concepts.

Unified framework for unsupervised concept extraction simplifies guarantees.

This work improves interpretability in deep learning models by introducing a two-level concept discovery framework.

We developed a caching method to speed up concept learning in complex knowledge bases.

CAVs reveal latent concept distributions, but are vulnerable to adversarial attacks.

A method for concept-based learning using probabilistic inference and expert rules.

Debias concept-based explanations by removing confounding information.

PCBM improves neural network generalization by partially observing concepts.