arXiv research

Paper uses RNNs to design LDPC codes for binary erasure channels.

Deep learning aids ADMM-based decoding for binary linear codes.

High-performance quantum codes decoded with minimal data.

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…

In this work, a deep learning-based method for log-likelihood ratio (LLR) lossy compression and quantization is proposed, with emphasis on a single-input single-output uncorrelated fading communication setting. A deep autoencoder network is trained to compress, quantize and reconstruct the bit log-likelihood ratios cor…

New quantum code breaks distance barrier with transversal non-Clifford gates.

A new approach for blind channel equalization and decoding, variational inference, and variational autoencoders (VAEs) in particular, is introduced. We first consider the reconstruction of uncoded data symbols transmitted over a noisy linear intersymbol interference (ISI) channel, with an unknown impulse response, with…

Low-density parity-check codes, a class of capacity-approaching linear codes, are particularly recognized for their efficient decoding scheme. The decoding scheme, known as the sum-product, is an iterative algorithm consisting of passing messages between variable and check nodes of the factor graph. The sum-product alg…

Topological theory for qLDPC codes enables non-Clifford gates and magic state injection.

New fault-tolerant quantum gates for homological LDPC codes with constant or almost-constant rate.

Recent developments in the field of deep learning have motivated many researchers to apply these methods to problems in quantum information. Torlai and Melko first proposed a decoder for surface codes based on neural networks. Since then, many other researchers have applied neural networks to study a variety of problem…

Efficiently clusters large datasets using low-density hyperplanes.

Quantum codes on hyperbolic lattices outperform Euclidean ones with higher rates and lower overhead.

New pruning methods improve dynamic sparse training performance.

Paper develops a method to create accurate emulators of expensive computer codes.

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…

This study analyzes how one-layer transformers learn regular language recognition tasks.

SDG uses optimal control to improve classifier guidance in low-density regions.

Proposes a framework to balance supervised and unsupervised learning using random matrix theory.

We consider the weighted belief-propagation (WBP) decoder recently proposed by Nachmani et al. where different weights are introduced for each Tanner graph edge and optimized using machine learning techniques. Our focus is on simple-scaling models that use the same weights across certain edges to reduce the storage and…

Improves generation of minority samples using diffusion models.

We present a new method of generating mixture models for data with categorical attributes. The keys to this approach are an entropy-based density metric in categorical space and annealing of high-entropy/low-density components from an initial state with many components. Pruning of low-density components using the entro…

GCAO improves clustering of high-dimensional data by grouping low-density boundary points.

In this paper, we study the problem of compressed sensing using binary measurement matrices and $\ell_1$-norm minimization (basis pursuit) as the recovery algorithm. We derive new upper and lower bounds on the number of measurements to achieve robust sparse recovery with binary matrices. We establish sufficient conditi…

L-Cool improves image and language translation by cooling low-density samples.

Boost-and-Skip generates minority samples without guidance, faster and more effectively.

New algorithm detects anomalies by forcing samples to displace mass in low-density regions.

Combines Xgboost and transductive SVM for semi-supervised learning.

The problem of inhomogeneous cluster densities has been a long-standing issue for distance-based and density-based algorithms in clustering and anomaly detection. These algorithms implicitly assume that all clusters have approximately the same density. As a result, they often exhibit a bias towards dense clusters in th…

Neural samplers such as variational autoencoders (VAEs) or generative adversarial networks (GANs) approximate distributions by transforming samples from a simple random source---the latent space---to samples from a more complex distribution represented by a dataset. While the manifold hypothesis implies that the densit…

MANO normalizes logits to estimate test accuracy without labels.

Random quotients of hyperbolic cubulated groups remain cubulated.

CycleCluster uses clustering to improve deep semi-supervised learning.

Study finds a linear lower bound on conformal dimension for random hyperbolic groups.

We introduce Interpolation Consistency Training (ICT), a simple and computation efficient algorithm for training Deep Neural Networks in the semi-supervised learning paradigm. ICT encourages the prediction at an interpolation of unlabeled points to be consistent with the interpolation of the predictions at those points…

In this paper we consider the problem of semi-supervised learning with deep Convolutional Neural Networks (ConvNets). Semi-supervised learning is motivated on the observation that unlabeled data is cheap and can be used to improve the accuracy of classifiers. In this paper we propose an unsupervised regularization term…

Super-AND improves unsupervised embedding learning with 89.2% accuracy on CIFAR-10.

We study optimal estimation for sparse principal component analysis when the number of non-zero elements is small but on the same order as the dimension of the data. We employ approximate message passing (AMP) algorithm and its state evolution to analyze what is the information theoretically minimal mean-squared error …

The paper exposes common misconceptions about OOD detection and proposes a new framework.

Density-based clustering is the task of discovering high-density regions of entities (clusters) that are separated from each other by contiguous regions of low-density. DBSCAN is, arguably, the most popular density-based clustering algorithm. However, its cluster recovery capabilities depend on the combination of the t…

Anomalies are intuitively easy for human experts to understand, but they are hard to define mathematically. Therefore, in order to have performance guarantees in unsupervised anomaly detection, priors need to be assumed on what the anomalies are. By contrast, active learning provides the necessary priors through approp…

New method for k-modes algorithm improves clustering performance.

Natural images are virtually surrounded by low-density misclassified regions that can be efficiently discovered by gradient-guided search --- enabling the generation of adversarial images. While many techniques for detecting these attacks have been proposed, they are easily bypassed when the adversary has full knowledg…

Lumbermark clusters data robustly, slicing limbs of mutual reachability trees.

We present a novel cost function for semi-supervised learning of neural networks that encourages compact clustering of the latent space to facilitate separation. The key idea is to dynamically create a graph over embeddings of labeled and unlabeled samples of a training batch to capture underlying structure in feature …

Discriminatively trained neural classifiers can be trusted, only when the input data comes from the training distribution (in-distribution). Therefore, detecting out-of-distribution (OOD) samples is very important to avoid classification errors. In the context of OOD detection for image classification, one of the recen…

Pantypes improve prototypical models by capturing diverse input distributions.

Graph construction is a crucial step in spectral clustering (SC) and graph-based semi-supervised learning (SSL). Spectral methods applied on standard graphs such as full-RBF, $ε$-graphs and $k$-NN graphs can lead to poor performance in the presence of proximal and unbalanced data. This is because spectral methods based…