Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,657 papers · 148 categories

Trend · papers per month

15294458 · Jun 202619922001200920172026
48 results for sign quantization

Note on subgaussian bounds for sign-quantized linear maps.

problem Understanding subgaussian behavior of sign-quantized linear maps.
method Developed a dimension-independent subgaussian concentration bound for Gaussian vectors under nonlinear mappings.
result Answered a question about sign-quantized linear maps using a new subgaussian bound.

Enhances LLM quantization with MDBF, improving perplexity and accuracy.

problem Limited performance of Double Binary Factorization in extreme quantization.
method Introduces Multi-envelope DBF, retaining sign matrices and replacing single envelope with rank-ll envelope.
result Improves perplexity and zero-shot accuracy over previous binary formats.

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

problem Quantization of neural nets with Swish activations, especially negative activations, leads to significant performance loss.
method Introduces learnable scale and offset parameters for asymmetric quantization, and uses MSE-based initialization for quantization parameters.
result Significantly outperforms LSQ for low-bit quantization of neural nets with Swish activations, achieving up to 5.6% gain with W2A2 quantization of EfficientNet-B0.

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

problem Accurately recovering vectors from 1-bit measurements using structured matrices.
method Correlation-based optimization with randomly signed partial Gaussian circulant matrices and generative models.
result Recovery guarantees match those for i.i.d. Gaussian matrices but with faster computation.

Federated learning (FL) has emerged as a prominent distributed learning paradigm. FL entails some pressing needs for developing novel parameter estimation approaches with theoretical guarantees of convergence, which are also communication efficient, differentially private and Byzantine resilient in the heterogeneous da…

2020-02-25abs ↗pdf ↗

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

problem Improving differential privacy in machine learning applications.
method Developed algorithms based on random projections and sign random projections, focusing on individual differential privacy (iDP) and standard differential privacy (DP).
result DP-SignOPORP and iDP-SignRP achieve superior performance in differential privacy, especially for small epsilon values.

A central machine is interested in estimating the underlying structure of a sparse Gaussian Graphical Model (GGM) from datasets distributed across multiple local machines. The local machines can communicate with the central machine through a wireless multiple access channel. In this paper, we are interested in designin…

2018-12-26abs ↗pdf ↗

Consider the recovery of an unknown signal x{x} from quantized linear measurements. In the one-bit compressive sensing setting, one typically assumes that x{x} is sparse, and that the measurements are of the form sign(ai,x){±1}\operatorname{sign}(\langle {a}_i, {x} \rangle) \in \{\pm1\}. Since such measurements give no informati…

2014-04-28abs ↗pdf ↗

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

problem Improving 2-bit covariance estimation with reduced operator norm error and no tuning needed.
method Proposed a new 2-bit covariance matrix estimator using triangular dithering scales.
result Improved operator norm error rate that depends on effective rank of covariance matrix, closing theoretical gap.

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

problem Estimating sparse vectors from noisy sign measurements in 1-bit compressed sensing.
method Binary Iterative Hard Thresholding (BIHT) algorithm, using Gaussian matrices and high-dimensional geometry analysis.
result BIHT provides estimates within ε+τ error with τ-fraction of incorrect measurements, maintaining universality of measurements.

A fast binary embedding method preserves Euclidean distances in high-dimensional data.

problem Preserving Euclidean distances in high-dimensional datasets.
method Stable noise-shaping quantization of AxA x with AA a sparse Gaussian random matrix, followed by a linear transformation.
result Euclidean distances are approximated by the 1\ell_1 norm on binary sequences, leading to accurate binary codes.

Let MM be an oriented even-dimensional Riemannian manifold on which a discrete group ΓΓ of orientation-preserving isometries acts freely, so that the quotient X=M/ΓX=M/Γ is compact. We prove a vanishing theorem for a half-kernel of a ΓΓ-invariant Dirac operator on a ΓΓ-equivariant Clifford module over MM, twisted by …

1998-09-24abs ↗pdf ↗

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

problem Support recovery in universal one-bit compressed sensing.
method Developed algorithms to recover the support of sparse signals with a small number of false positives.
result Support recovery with ildeO(k3/2) ilde{O}(k^{3/2}) measurements, improving to ildeO(k) ilde{O}(k) with known dynamic range.

The paper classifies quantizable functions and explores symmetry in quantization methods.

problem Classifying quantizable functions and understanding symmetry in quantization methods.
method Deformation quantization and geometric quantization methods are compared and classified.
result Formal quantizable functions are of a specific form and relate to Hamiltonian Killing vector fields.

This paper introduces a differentiable, scalable quantization method for neural networks.

problem Previous quantization methods lacked differentiability and scalability.
method The approach is differentiable and scalable, using bit-shifting and logarithmic quantization.
result The method achieves comparable accuracy to state-of-the-art approaches with less training time and lower inference cost.

StatQAT optimizes quantization for deep networks, reducing computational cost and memory usage.

problem Optimal quantization parameters selection for deep neural networks with diverse data distributions.
method Statistical error analysis framework for uniform and floating-point quantization, iterative and analytic quantizers designed for arbitrary and Gaussian-like distributions.
result Improved accuracy and stability in training low-precision neural networks.

This study optimizes quantized neural networks by considering model architecture and quantization types.

problem Optimizing quantized neural networks for low-power, high-throughput applications.
method Holistic approach including training methods and quantization-friendly architecture design.
result Deeper models are more sensitive to activation quantization, while wider models improve resilience to both weight and activation quantization.

Study on signed graphs with random signs, focusing on community detection.

problem Community detection in signed stochastic block models.
method Strong concentration inequalities for adjacency and Laplacian matrices, applied to signed Laplacian matrix.
result The sign of the first eigenvector of the Laplacian matrix defines a weakly consistent estimator for balanced community detection.

SELO model predicts link signs better than SDGNN using subgraph encoding and linear optimization.

problem Inferring the sign of links in signed networks with limited sign data.
method Subgraph Encoding via Linear Optimization (SELO) approach to learn edge embeddings.
result SELO model outperforms state-of-the-art methods on multiple real-world signed networks.

We argue that the standard graph Laplacian is preferable for spectral partitioning of signed graphs compared to the signed Laplacian. Simple examples demonstrate that partitioning based on signs of components of the leading eigenvectors of the signed Laplacian may be meaningless, in contrast to partitioning based on th…

2017-01-05abs ↗pdf ↗

HMQ improves quantization for edge devices with mixed precision.

problem Efficient quantization for edge devices with uniform, power-of-two thresholds.
method Introduces HMQ, a mixed precision quantization block that repurposes Gumbel-Softmax for searching over quantization schemes.
result Achieves competitive and state-of-the-art results on ImageNet despite restrictions.

Novel GNN for signed and directed networks using magnetic signed Laplacian.

problem Efficiently modeling signed and directed networks for tasks like clustering and link prediction.
method Introduced a magnetic signed Laplacian for directed signed graphs, used it to construct a spectral GNN.
result Demonstrated effective performance on tasks involving signed and directional information.

We present Rotated Adaptive Tetra-iterated Quantizer (RATQ), a fixed-length quantizer for gradients in first order stochastic optimization. RATQ is easy to implement and involves only a Hadamard transform computation and adaptive uniform quantization with appropriately chosen dynamic ranges. For noisy gradients with al…

2019-08-22abs ↗pdf ↗

The paper studies quantization on symplectic manifolds with real polarizations, comparing different quantization methods.

problem Quantization on compact symplectic manifolds with real polarizations.
method Geometric quantization, Toeplitz operators, Fourier transforms, asymptotic expansion of traces.
result Deformation quantization is realized through asymptotic traces of Toeplitz operators.

Unified finetuning of all quantization degrees of freedom achieves state-of-the-art 4-bit quantization.

problem Achieving high accuracy in quantized neural networks while maintaining speed and resource constraints.
method Quantization-aware finetuning (QFT) that jointly optimizes all quantization degrees of freedom.
result 4-bit weight quantization results on-par with state-of-the-art (SoTA) within PTQ constraints.

Sign equivariant networks improve model expressiveness for spectral geometric learning.

problem Limited expressiveness of sign invariant models for tasks like graph link prediction.
method Developed sign equivariant neural network architectures based on new analytic sign equivariant polynomials.
result Sign equivariant models achieve theoretical benefits in spectral geometric learning tasks.

Neural network models are resource hungry. It is difficult to deploy such deep networks on devices with limited resources, like smart wearables, cellphones, drones, and autonomous vehicles. Low bit quantization such as binary and ternary quantization is a common approach to alleviate this resource requirements. Ternary…

2019-09-26abs ↗pdf ↗

Geometric quantization of a Poisson manifold need not imply quantization of its symplectic leaves. We provide the leafwise geometric quantization of a Poisson manifold, seen as a foliated one, whose quantum algebra restricted to each leaf is quantized.

2001-10-18abs ↗pdf ↗

Study quantization effects on high-dimensional linear regression learning.

problem Understanding quantization's impact on learning high-dimensional linear regression models.
method Analyzes stochastic gradient descent for high-dimensional linear regression under various quantization targets.
result Establishes precise bounds on excess risk for different quantization schemes.

FrostNet improves INT8 quantization efficiency in mobile networks.

problem The importance of network architecture for optimal INT8 quantization.
method Quantization-aware training (QAT) with StatAssist and GradBoost, hardware-aware NAS.
result FrostNets achieve higher recognition accuracy with comparable latency when quantized.