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.

168,695 papers · 148 categories

Trend · papers per month

105210314419 · Jun 202019922001200920172026
48 results for uniform accuracy

Learning ReLU networks to high uniform accuracy requires exponentially many samples.

problem Achieving high uniform accuracy on ReLU networks for security-critical applications.
method Quantified the number of training samples needed for any algorithm to guarantee uniform accuracy.
result The minimal number of training samples scales exponentially with network depth and input dimension.

Improved sampling accuracy in SG-MCMC methods via non-uniform gradient subsampling.

problem Computational inefficiency and sampling error in stochastic gradient MCMC methods.
method Proposes a non-uniform subsampling scheme to reduce sampling error in EWSG, a variant of SG-MCMC.
result EWSG reduces sampling error compared to uniform subsampling, improving accuracy without sacrificing convergence speed.

Sparsity in Deep Neural Networks (DNNs) is studied extensively with the focus of maximizing prediction accuracy given an overall parameter budget. Existing methods rely on uniform or heuristic non-uniform sparsity budgets which have sub-optimal layer-wise parameter allocation resulting in a) lower prediction accuracy o…

2020-02-08abs ↗pdf ↗

UCPO improves diversity in reinforcement learning models, maintaining high accuracy.

problem RLVR objectives often lead to diversity collapse, reducing coverage of correct solutions.
method UCPO adds a conditional uniformity penalty to GRPO, redistributing probability mass.
result UCPO improves Pass@K and diversity while maintaining competitive Pass@1 accuracy.

New algorithm achieves strong consistency in binary non-uniform hypergraph classification.

problem Node classification on binary non-uniform hypergraphs with varying edge probabilities.
method Proposes a refinement algorithm using power iteration on weighted adjacency matrices.
result Proves optimality of the refinement algorithm, achieving strong consistency and IT lower bound.

New algorithms achieve uniform-PAC guarantees for RL with bounded eluder dimension.

problem Achieving strong performance guarantees in reinforcement learning.
method Proposes algorithms for nonlinear bandits and model-based episodic RL with a bounded eluder dimension.
result Achieves uniform-PAC sample complexity that matches state-of-the-art regret bounds or sample complexity guarantees.

Uniform Closure Method and Bayes classifier perform similarly in classifying open knots.

problem Classifying knots in open macromolecular chains.
method Used the Bayes MAP classifier and compared it to the Uniform Closure Method.
result Both methods have comparable accuracy and positive predictive value.

Residual neural networks don't help overcome sampling complexity issues.

problem Learning invertible residual neural networks from samples is hard due to the curse of dimensionality.
method Investigated invertible residual neural networks and their sampling complexity.
result Invertible residual neural networks still suffer from the curse of dimensionality in sampling complexity.

This paper improves binary classification methods beyond accuracy, especially in imbalanced datasets.

problem Binary classification performance metrics often fail to reflect real-world consequences, especially in imbalanced datasets.
method Derives a generalized Bayes-optimal classifier from accuracy to any performance metric, removing assumptions and providing finite-sample statistical guarantees.
result Optimal classification performance depends on class imbalance properties, providing new insights and guarantees.

The paper provides a uniform convergence bound for smooth calibration error and its relationship with functional gradient.

problem Limited theoretical understanding of learning algorithms achieving high accuracy and good calibration.
method Focuses on smooth calibration error, providing a uniform convergence bound and proving the relationship with functional gradient.
result Derives conditions for simultaneous classification and calibration guarantees in gradient boosting trees, kernel boosting, and neural networks.

Paper proposes a learning-based sparse Bayesian method for accurate off-grid DOA estimation.

problem One-bit off-grid direction of arrival (DOA) estimation in a single snapshot scenario.
method Formulated off-grid DOA estimation model, used Sparse Bayesian framework, proposed Learning-based Sparse Bayesian approach.
result Improved computational efficiency and accuracy in off-grid DOA estimation.

As an efficient and scalable graph neural network, GraphSAGE has enabled an inductive capability for inferring unseen nodes or graphs by aggregating subsampled local neighborhoods and by learning in a mini-batch gradient descent fashion. The neighborhood sampling used in GraphSAGE is effective in order to improve compu…

2019-04-29abs ↗pdf ↗

Gaussian Mixture Models are one of the most studied and mature models in unsupervised learning. However, outliers are often present in the data and could influence the cluster estimation. In this paper, we study a new model that assumes that data comes from a mixture of a number of Gaussians as well as a uniform ``back…

2018-04-08abs ↗pdf ↗

Researchers study fairness-accuracy tradeoffs in predictive models for multiple groups.

problem Understanding the tradeoff between fairness and accuracy in models serving multiple demographic groups.
method Characterizing the fairness-accuracy (FA) Pareto frontier, approximating it from limited data, and bounding the worst-case gap.
result Derivation of worst-case-optimal estimators and uniform finite-sample bounds for the entire FA frontier.

New findings show neural networks can be fooled by adversarial data, but a simple bias fix works.

problem Neural networks can be misled by adversarial data, rendering existing generalization bounds ineffective.
method Extensive theoretical investigation of a specific dataset using infinitely-wide models, focusing on the Neural Tangent Kernel (NTK).
result A sensible choice of output bias completely mitigates the adversarial phenomenon, revealing phase transitions in accuracy.

Continuous representations have been widely adopted in recommender systems where a large number of entities are represented using embedding vectors. As the cardinality of the entities increases, the embedding components can easily contain millions of parameters and become the bottleneck in both storage and inference du…

2019-11-05abs ↗pdf ↗

Enhances privacy in federated learning with Laplacian smoothing.

problem Protecting data privacy in federated learning while maintaining model accuracy.
method Laplacian smoothing for differentially private federated learning (DP-Fed-LS).
result Improves model accuracy with differential privacy guarantee and membership privacy.

New method improves active statistical inference by reducing noise.

problem Inaccurate uncertainty estimates in active sampling lead to noisy results.
method Robust sampling strategies that interpolate between uniform and active sampling based on uncertainty scores.
result The robust sampling ensures that the estimator is never worse than uniform sampling and usually outperforms active inference.

Deep neural nets approximate random dynamical system trajectories uniformly in time.

problem Approximating trajectories of random dynamical systems over infinite time horizons.
method Recurrent neural networks with simple feedback structures.
result Certain random trajectories can be approximated uniformly in time to any desired accuracy.

The study evaluates different probability models for uncertainty visualization using entropy calculations.

problem Choosing the right probability model affects memory use, run time, and accuracy in uncertainty visualization.
method Entropy calculation on ensemble data to compare various probability models (uniform, Gaussian, histogram, quantile).
result Models matching the ensemble data distribution have the lowest entropy, indicating better accuracy.

Paper extracts features from time series to improve forecasting accuracy.

problem Forecasting time series generated by Itô-type processes with unknown coefficients.
method Statistical adjustment of mixture-type models to extract features from time series data.
result Additional statistical features enhance time series prediction accuracy.

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 ↗

Subsampled Randomized Hadamard Transform (SRHT), a popular random projection method that can efficiently project a dd-dimensional data into rr-dimensional space (rdr \ll d) in O(dlog(d))O(dlog(d)) time, has been widely used to address the challenge of high-dimensionality in machine learning. SRHT works by rotating the input …

2020-02-05abs ↗pdf ↗

We revisit Spakula's uniform K-homology, construct the external product for it and use this to deduce homotopy invariance of uniform K-homology. We define uniform K-theory and on manifolds of bounded geometry we give an interpretation of it via vector bundles of bounded geometry. We further construct a cap product with…

2018-08-23abs ↗pdf ↗

New hypergraph neural network learns variable-sized hyperedges.

problem Learning representations for non-uniform hypergraphs with variable cardinalities.
method Developed a hypergraph neural network exploiting incidence structure.
result Significant improvement in accuracy on real-world hypergraph datasets.

Proposes a tensor Laplacian-based method for better subspace clustering of non-uniformly distributed data.

problem LRR's inability to handle non-uniform data distribution and local information loss.
method Tensor Laplacian Regularized Low-Rank Representation (TLRR) using hypergraph model and tensor Laplacian algorithm.
result Higher accuracy and precision in subspace clustering compared to state-of-the-art methods.

In "Rips complexes and covers in the uniform category" \cite{Rips} the authors define, following James \cite{J}, covering maps of uniform spaces and introduce the concept of generalized uniform covering maps. Conditions for the existence of universal uniform covering maps and generalized uniform covering maps are given…

2010-08-02abs ↗pdf ↗

This paper refines homotopy theory for cubical sets and uniform spaces.

problem Classical homotopy theory limitations in cubical sets and uniform spaces.
method Develops a uniform-theoretic refinement for cubical sets and uniform spaces, lifting to a full and faithful embedding.
result Lifts classical homotopy categories to new uniform homotopy categories, generalizing cohomology theories.

The study examines how much data is needed for generative and vision-language models to make reliable predictions.

problem Ensuring reliable predictions with low data for models used in medical decision support.
method Analyzes uniform convergence bounds for VLM-induced classifiers under low-dimensional semantic representations.
result Finite-sample uniform convergence bounds for accuracy and calibration functionals of VLM-induced classifiers.

Study shows gap between uniform convergence and test error in random feature models.

problem Understanding the gap between uniform convergence and test error in random feature models.
method Analytical expressions for uniform convergence over norm balls, interpolators, and minimum norm interpolator risk derived and proved.
result Uniform convergence over interpolators still gives a non-trivial bound of test error even when classical uniform convergence is vacuous.

Develops a framework for distilling flow models from few steps.

problem Improving few-step sampling in diffusion models for better performance.
method Local approximation errors and dynamical amplification controlled through analytical tractability.
result Deep residual compositions efficiently approximate long-horizon transport with controlled global error.