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.

169,291 papers · 148 categories

Trend · papers per month

59119178237 · Jun 202019922001200920182026
48 results for single-bit weights

Wide residual networks achieve low error rates with single-bit weights.

problem Deploying deep neural networks on resource-constrained hardware with low memory.
method Binarizing weights using sign function and scaling factors, applying warm-restart learning rate schedule.
result Achieved error rates of 3.9% on CIFAR-10, 18.5% on CIFAR-100, and 26.0% on ImageNet with 1-bit-per-weight.

Improved SNNs with quantized activations outperform traditional networks.

problem Maintaining SotA accuracy in SNNs with limited bit precision.
method Interpolating between non-spiking and spiking regimes using signal processing tools.
result First hybrid SNN outperforms traditional RNNs in accuracy with reduced bit precision.

Paper studies signal detection in noisy environments with limited communication.

problem Signal detection in Gaussian noise with 1-bit communication constraints.
method Derives lower bounds and exhibits optimal testing strategies.
result Optimal distributed testing strategies attain the derived lower bound.

Paper proposes efficient BNN inference techniques on FPGA.

problem Redundancy in BNN inference leading to high computation and data access costs.
method Analyzed image similarity and BNN kernel weights to exploit redundancy. Proposed two types of fast and energy-efficient architectures.
result 80% reduction in computation and 40% in buffer access, achieving 17% power reduction.

Regularized linear regression improves binary classification performance, especially with ridge and 1\ell_1 regularization.

problem Improving binary classification accuracy with noisy labels.
method Systematic study of regularization strengths on linear classifiers trained on noisy binary classification data.
result Ridge regression consistently improves classification error, while 1\ell_1 regularization can induce sparsity and \ell_\infty regularization can concentrate weights to two values.

BENN improves binary neural networks by ensemble methods, boosting accuracy without sacrificing efficiency.

problem Inefficiency and accuracy degradation in binary neural networks.
method Proposes Binary Ensemble Neural Network (BENN) using ensemble techniques.
result BENN outperforms state-of-the-art binary networks and full-precision networks.

New approach replaces BN layers with shifted-ReLU for embedded systems.

problem Complexity and overheads of BN layers in low-power embedded systems.
method Used shifted-ReLU layers instead of BN layers in wide residual networks.
result Shifted-ReLU layers offer advantages in speed, memory, and complexity without significant accuracy loss.

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

problem Stochastic linear bandits with 1-bit communication constraints.
method Phased-elimination algorithms based on G-optimal designs and 1-bit mean estimation.
result Achieves near-optimal regret bounds for broad scaling regimes.

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.

A study on distributed mean estimation with trade-offs between communication and accuracy.

problem Estimating the arithmetic average of distributed vectors with limited communication.
method Proposes a flexible family of randomized algorithms exploring the trade-off between communication cost and estimation error.
result Improves error rate to O(r/n)\mathcal{O}(r/n) when communicating a single bit per coordinate, where rr is the bit representation of a floating point value.

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

problem Estimating the mean of a symmetric log-concave distribution with limited one-bit measurements.
method Analyzes mean squared error in three settings: centralized, adaptive, and distributed, with and without quantization.
result One round of adaptivity is sufficient to achieve optimal mean-square error in the adaptive setting.

SATNet integrates logical reasoning into deep learning with a differentiable MAXSAT solver.

problem Integrating logical reasoning into deep learning architectures.
method Differentiable MAXSAT solver based on fast coordinate descent for SDP.
result Minimally supervised learning of logical structures in deep learning systems.

Linear regression studies the problem of estimating a model parameter βRpβ^* \in \mathbb{R}^p, from nn observations {(yi,xi)}i=1n\{(y_i,\mathbf{x}_i)\}_{i=1}^n from linear model yi=xi,β+εiy_i = \langle \mathbf{x}_i,β^* \rangle + ε_i. We consider a significant generalization in which the relationship between $\langle \mathbf{x}_i,β^* \ran…

2015-05-13abs ↗pdf ↗

Deep learning improves one-bit OFDM receiver performance.

problem One-bit quantization complicates accurate channel estimation and data detection in OFDM receivers.
method Developed deep neural networks for channel estimation and data detection, using a two-step training policy.
result Deep learning-based designs achieve lower BER than unquantized OFDM at moderate SNRs.

A multi-player bandit system resists adversarial attacks with near-optimal regret.

problem Adversaries attempt to manipulate rewards in a multi-player multi-armed bandit game.
method Players communicate a single bit to resist attacks, achieving near-optimal regret.
result Achieves near-optimal regret of O(log1+δT+W)O(\log^{1+δ}T + W), where WW is the total time of adversarial attacks.

Model uses Preisach hysteresis to predict gig worker acceptance, reducing costs and improving fill rates.

problem Predicting and optimizing gig worker acceptance in labor markets.
method Preisach hysteresis model applied to neural network and XGBoost classifier for binary transaction outcomes.
result Model reduces total wage bill by 21.3% and increases expected fill rate by 9.7 pp.

A new weighted MCC measure improves classifier performance evaluation.

problem Lack of measures sensitive to observation weights in multiclass classification.
method Proposes weighted versions of Pearson-Matthews Correlation Coefficient (MCC) for binary and multiclass classification.
result Weighted MCC values are higher for classifiers that perform better on highly weighted observations.

Develops theory of weightings for Lie groupoids and algebroids.

problem Understanding differential geometry of weightings for Lie groupoids and algebroids.
method Extending work on weighted manifolds, defining weighted submanifolds, and developing theories of linear weightings and multiplicative weightings.
result Characterizes infinitesimally multiplicative weightings for Lie algebroids and classifies multiplicative weightings of Lie groupoids.

The paper extends spin geometry to weighted manifolds and defines a new mass for Ricci flow.

problem Generalizing spin geometry to weighted manifolds and defining a new mass.
method Investigates spectral properties of the weighted Dirac operator and defines a new mass.
result Defines a new mass for weighted asymptotically Euclidean manifolds and shows its monotonicity under Ricci flow.

The study explores weightings on submanifolds and their geometric properties.

problem Understanding weightings on submanifolds and their geometric implications.
method Detailed exploration of weighted normal bundles, weighted deformation spaces, and weighted blow-ups.
result A description of weightings in terms of subbundles of higher tangent bundles, leading to new concepts for Lie algebroids and groupoids.

Defines and proves properties of weighted renormalized volume coefficients.

problem None explicitly stated; focuses on mathematical definitions and proofs.
method Defines weighted renormalized volume coefficients and proves their variational nature and polynomial representation.
result Weighted renormalized volume coefficients are variational and can be expressed as polynomials of specific tensors.

Method measures weight similarity in neural networks using normalization and statistical inference.

problem Quantifying weight similarity in non-convex neural networks.
method Chain normalization rule and hypothesis-training-testing statistical inference.
result Weights of identical neural networks converge to similar local solutions.

Study on stable minimal hypersurfaces under Ricci curvature constraints.

problem Stability of weighted minimal hypersurfaces under Ricci curvature bounds.
method Derive geometric consequences and prove a Schoen-Yau type criterion.
result Structure theorem for three-dimensional weighted manifolds of non-negative Ricci curvature.

The paper classifies vertices in weighted networks using spectral embedding and edge weight distributions.

problem Classifying vertices in weighted networks where edge weights and adjacencies encode class membership.
method Introduced a edge weight distribution matrix to the K-Block Stochastic Block Model for weighted networks. Developed classification procedures based on spectral embedding of the unweighted adjacency matrix under two assumptions on edge weight distributions.
result Proposed classifiers outperform quadratic discriminant analysis on transformed weighted networks.

The study establishes comparison theorems for weighted Finsler manifolds and spacetimes.

problem Analyzing weighted Finsler manifolds and spacetimes with curvature conditions.
method Using weight function and εε-range, the Bonnet-Myers theorem, Laplacian comparison theorem, and Bishop-Gromov volume comparison theorem are formulated.
result New comparison theorems for weighted Finsler manifolds and spacetimes are derived, including those for weighted Riemannian manifolds.

A new method compresses deep neural networks by predicting and quantizing weights between layers.

problem Resource constraints in deep neural networks.
method Inter-Layer Weight Prediction (ILWP) and quantization based on Smoothly Varying Weight Hypothesis (SVWH).
result The method achieves higher weight compression rates at the same accuracy level.

The paper generalizes K-stability results to singular and weighted settings.

problem Generalizing K-stability to singular and weighted settings.
method Generalization of results in \cite{Li22a} to singular and weighted settings.
result The \(\mathbb{G}\)-uniform weighted K-stability for models implies \(\mathbb{G}\)-coercivity of the weighted Mabuchi functional.

The study analyzes weighted manifolds with curvature bounds, proving eigenvalue estimates and inequalities.

problem Analyzing geometric properties of weighted manifolds under Ricci curvature bounds.
method Develops geometric analysis techniques on weighted Riemannian manifolds with lower 00-weighted Ricci curvature bounds.
result Proves eigenvalue estimates for Steklov and ABP inequalities on weighted manifolds.

Study on deformation of weighted scalar curvature, proving geometric results and stability.

problem Deformation of weighted scalar curvature and related geometric properties.
method Linearization of weighted scalar curvature, studying kernel of formal adjoint.
result Definition and study of weighted vacuum static spaces, stability results on flat spaces.

New algorithms avoid weight transport, outperforming current deep learning methods.

problem Current deep learning algorithms rely on weight transport, which is biologically implausible.
method Two mechanisms: weight mirror and modified Kolen-Pollack algorithm, using random feedback weights.
result These mechanisms outperform feedback alignment and other methods on visual recognition tasks.

The Penrose theorem and Hawking's topology theorem are extended to weighted spacetimes.

problem Extending Penrose's singularity theorem and Hawking's topology theorem to weighted spacetimes.
method Using weighted null energy condition and synthetic dimension to generalize the theorems.
result Generalized versions of the Penrose and Hawking theorems hold under a weighted null energy condition.