arXiv research

Paper offers robust recovery for 1-bit sensing with partial Gaussian circulant matrices.

Enhances LLM quantization with MDBF, improving perplexity and accuracy.

Paper analyzes BIHT for noisy 1-bit CS, improving results with up to τ-fraction of incorrect measurements.

This paper resolves BIHT convergence, showing normalization is not necessary in noiseless settings but crucial for robustness.

This letter proposes a sparse diffusion steepest-descent algorithm for one bit compressed sensing in wireless sensor networks. The approach exploits the diffusion strategy from distributed learning in the one bit compressed sensing framework. To estimate a common sparse vector cooperatively from only the sign of measur…

This letter proposes a dictionary learning algorithm for blind one bit compressed sensing. In the blind one bit compressed sensing framework, the original signal to be reconstructed from one bit linear random measurements is sparse in an unknown domain. In this context, the multiplication of measurement matrix $\Ab$ an…

PPC learns binary codes from data similarities and dissimilarities.

New algorithm sets record for model evasion with minimal queries.

Paper proves a new lower bound on calibration error for binary prediction.

LSQ+ improves quantization of neural nets with Swish activations, achieving state-of-the-art results.

Improves bit error tolerance in RRAM-based BNNs without overfitting.

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

Consider the recovery of an unknown signal ${x}$ from quantized linear measurements. In the one-bit compressive sensing setting, one typically assumes that ${x}$ is sparse, and that the measurements are of the form $\operatorname{sign}(\langle {a}_i, {x} \rangle) \in \{\pm1\}$. Since such measurements give no informati…

This letter presents the sparse vector signal detection from one bit compressed sensing measurements, in contrast to the previous works which deal with scalar signal detection. In this letter, available results are extended to the vector case and the GLRT detector and the optimal quantizer design are obtained. Also, a …

Social trust prediction addresses the significant problem of exploring interactions among users in social networks. Naturally, this problem can be formulated in the matrix completion framework, with each entry indicating the trustness or distrustness. However, there are two challenges for the social trust problem: 1) t…

Improves matrix multiplication throughput for asymmetric bit-width operands.

Stochastic gradient descent (SGD) is one of the most widely used optimization methods for parallel and distributed processing of large datasets. One of the key limitations of distributed SGD is the need to regularly communicate the gradients between different computation nodes. To reduce this communication bottleneck, …

Study on recovering sparse linear classifiers from mixed binary responses.

In this paper, the problem of one-bit compressed sensing (OBCS) is formulated as a problem in probably approximately correct (PAC) learning. It is shown that the Vapnik-Chervonenkis (VC-) dimension of the set of half-spaces in $\mathbb{R}^n$ generated by $k$-sparse vectors is bounded below by $k \lg (n/k)$ and above by…

Improved 2-bit covariance estimator with reduced operator norm error and no tuning needed.

Two algorithms improve federated learning efficiency and resilience.

For fast and energy-efficient deployment of trained deep neural networks on resource-constrained embedded hardware, each learned weight parameter should ideally be represented and stored using a single bit. Error-rates usually increase when this requirement is imposed. Here, we report large improvements in error rates …

We study the use of "sign $α$-stable random projections" (where $0<α\leq 2$) for building basic data processing tools in the context of large-scale machine learning applications (e.g., classification, regression, clustering, and near-neighbor search). After the processing by sign stable random projections, the inner pr…

Binary Iterative Hard Thresholding converges with optimal number of 1-bit measurements.

RFML systems are vulnerable to adversarial attacks, especially in OTA transmissions.

The paper introduces DP algorithms using random projections and sign random projections for improved privacy in machine learning.

This paper improves support recovery in universal one-bit compressed sensing with fewer measurements.

This paper improves support recovery in universal one-bit compressed sensing.

Locality-sensitive hashing converts high-dimensional feature vectors, such as image and speech, into bit arrays and allows high-speed similarity calculation with the Hamming distance. There is a hashing scheme that maps feature vectors to bit arrays depending on the signs of the inner products between feature vectors a…

New techniques improve 16-bit training accuracy without 32-bit units.

Bayesian Bits unifies quantization and pruning through gradient optimization.

Many state-of-the-art results obtained with deep networks are achieved with the largest models that could be trained, and if more computation power was available, we might be able to exploit much larger datasets in order to improve generalization ability. Whereas in learning algorithms such as decision trees the ratio …

Low-bit training framework reduces energy consumption in CNNs.

Low bit-width weights and activations are an effective way of combating the increasing need for both memory and compute power of Deep Neural Networks. In this work, we present a probabilistic training method for Neural Network with both binary weights and activations, called BLRNet. By embracing stochasticity during tr…

Bit-Swap improves lossless compression for hierarchical latent variable models.

Paper improves DNN accelerator robustness against bit errors with energy savings.

Bit-slice sparsity improves ReRAM-based DNN acceleration.

The state-of-the-art hardware platforms for training Deep Neural Networks (DNNs) are moving from traditional single precision (32-bit) computations towards 16 bits of precision -- in large part due to the high energy efficiency and smaller bit storage associated with using reduced-precision representations. However, un…

Estimating mean from one-bit samples of symmetric log-concave distributions.

Majority bit estimation in noisy random recursive DAGs.

Paper proposes a CNN-based method for estimating intra frame bits and quality.

Paper proposes a hybrid model-based and data-driven approach for one-bit compressive autoencoding.

Paper proposes a hybrid model-based and data-driven method for one-bit compressive variational autoencoding.

Paper proposes training deep neural networks with 8-bit floating point precision.

New protocols show 1-bit mean estimation can be order-optimal without interaction.

Topological data analysis classifies encrypted bits with success.

One-bit feedback suffices for a bandit problem's optimal strategy.

New algorithm tackles batched stochastic linear bandits with 1-bit communication constraints.