arXiv research

Proposes a method to improve Byzantine-robustness in compressed federated learning.

Paper shows how to integrate quantization into neural compression models.

BNCR-GAN improves GANs to generate clean images from degraded inputs.

Unified framework for distributed compressed SGD under $(L_0, L_1)$-smoothness.

DiffC compresses images by diffusing Gaussian noise, outperforming state-of-the-art methods.

Compression is at the heart of effective representation learning. However, lossy compression is typically achieved through simple parametric models like Gaussian noise to preserve analytic tractability, and the limitations this imposes on learning are largely unexplored. Further, the Gaussian prior assumptions in model…

This work considers an estimation task in compressive sensing, where the goal is to estimate an unknown signal from compressive measurements that are corrupted by additive pre-measurement noise (interference, or clutter) as well as post-measurement noise, in the specific setting where some (perhaps limited) prior knowl…

SignSGD analysis quantifies its effects in high dimensions.

Gradient sparsification enhances privacy-preserving machine learning models.

Differentiable model compression adds noise to parameters during training.

Compressed LLM embeddings improve noisy regression tasks without overfitting.

We solve image inverse problems using a flow-based noise model.

We consider the distributional connection between the lossy compressed representation of a high-dimensional signal $X$ using a random spherical code and the observation of $X$ under an additive white Gaussian noise (AWGN). We show that the Wasserstein distance between a bitrate-$R$ compressed version of $X$ and its obs…

Turbo-DDCM speeds up zero-shot image compression.

We extend quantization-aware training to extreme model compression.

New findings show learnable distributions remain learnable even with noisy or adversarial perturbations.

The paper provides theoretical guarantees for optimized sampling in compressed sensing, showing error vanishes with more measurements.

New SGD variant makes neural networks compressible without assumptions.

We provide recovery guarantees for compressible signals that have been corrupted with noise and extend the framework introduced in \cite{bafna2018thwarting} to defend neural networks against $\ell_0$-norm, $\ell_2$-norm, and $\ell_{\infty}$-norm attacks. Our results are general as they can be applied to most unitary tr…

Randomized matrix compression techniques, such as the Johnson-Lindenstrauss transform, have emerged as an effective and practical way for solving large-scale problems efficiently. With a focus on computational efficiency, however, forsaking solutions quality and accuracy becomes the trade-off. In this paper, we investi…

Paper tackles noisy labels by compressing feature representations.

We provide a comprehensive review of classical algorithms for compressive sensing of images, focused on Total variation methods, with a view to application in LiDAR systems. Our primary focus is providing a full review for beginners in the field, as well as simulating the kind of noise found in real LiDAR systems. To t…

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…

Improved diffusion models achieve state-of-the-art likelihoods in image density estimation.

Unified sign-based compression for federated learning with faster convergence.

Paper analyzes convergence rates of compressed LSR algorithms in federated learning.

We study the localization of a cluster of activated vertices in a graph, from adaptively designed compressive measurements. We propose a hierarchical partitioning of the graph that groups the activated vertices into few partitions, so that a top-down sensing procedure can identify these partitions, and hence the activa…

Recovering the support of sparse vectors in underdetermined linear regression models, \textit{aka}, compressive sensing is important in many signal processing applications. High SNR consistency (HSC), i.e., the ability of a support recovery technique to correctly identify the support with increasing signal to noise rat…

OptiNet achieves near-minimax error rates with compression in Euclidean space.

NAC-FL optimizes model updates in FL systems by adapting compression to network congestion.

A new memory-efficient Adam variant reduces second moments when feasible.

FedSGM tackles constrained federated learning with unified framework.

This paper deals with two related problems, namely distance-preserving binary embeddings and quantization for compressed sensing . First, we propose fast methods to replace points from a subset $\mathcal{X} \subset \mathbb{R}^n$, associated with the Euclidean metric, with points in the cube $\{\pm 1\}^m$ and we associa…

This paper proposes a simple adaptive sensing and group testing algorithm for sparse signal recovery. The algorithm, termed Compressive Adaptive Sense and Search (CASS), is shown to be near-optimal in that it succeeds at the lowest possible signal-to-noise-ratio (SNR) levels, improving on previous work in adaptive comp…

AdaBoost improves binary classification in robust one-bit compressed sensing with adversarial errors.

Study 1-bit compressive sensing with generative models, improving recovery accuracy.

Artemis framework improves distributed learning with bidirectional compression and partial participation.

In this paper, we investigate the robust dictionary learning (DL) to discover the hybrid salient low-rank and sparse representation in a factorized compressed space. A Joint Robust Factorization and Projective Dictionary Learning (J-RFDL) model is presented. The setting of J-RFDL aims at improving the data representati…

The paper proposes a least squares method for binary compressive sampling with low intrinsic dimension signals.

In this paper, we derive Hybrid, Bayesian and Marginalized Cramér-Rao lower bounds (HCRB, BCRB and MCRB) for the single and multiple measurement vector Sparse Bayesian Learning (SBL) problem of estimating compressible vectors and their prior distribution parameters. We assume the unknown vector to be drawn from a compr…

New method preserves privacy while improving machine learning accuracy.

Fetal ECG (FECG) telemonitoring is an important branch in telemedicine. The design of a telemonitoring system via a wireless body-area network with low energy consumption for ambulatory use is highly desirable. As an emerging technique, compressed sensing (CS) shows great promise in compressing/reconstructing data with…

We propose a joint source and channel coding (JSCC) technique for wireless image transmission that does not rely on explicit codes for either compression or error correction; instead, it directly maps the image pixel values to the complex-valued channel input symbols. We parameterize the encoder and decoder functions b…

Improves convergence speed in compressive sensing with a new probabilistic approach.

New biased compression methods lead to faster convergence in distributed learning.

Network agents solve adaptive regression problems with compressed signals.

Datasets such as images, text, or movies are embedded in high-dimensional spaces. However, in important cases such as images of objects, the statistical structure in the data constrains samples to a manifold of dramatically lower dimensionality. Learning to identify and extract task-relevant variables from this embedde…

R2T hybrid model improves robust regression for asymmetric noise.