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.

169,236 papers · 148 categories

Trend · papers per month

count % of corpus

48 results for “linear model approximation”

Improving the Linearized Laplace Approximation via Quadratic Approximationsstat.ML

QLA improves Bayesian uncertainty estimation for DNNs without increasing computational cost.

problem Overconfident out-of-distribution predictions from DNNs.

method Proposes Quadratic Laplace Approximation (QLA) to improve Bayesian uncertainty quantification.

result QLA yields modest yet consistent uncertainty estimation improvements over Linearized Laplace Approximation (LLA) on five regression datasets.

Bayesian uncertainty Deep neural networks Quadratic approximation Laplace approximation Prediction

2026-02-03abs ↗pdf ↗

Non-linear reduced modeling of dynamical systems using kernel methods and low-rank approximationstat.ML

This work proposes a new algorithm for efficient reduced modeling of non-linear dynamical systems.

problem Reduced modeling of computationally demanding dynamical systems to balance accuracy and complexity.

method Embedding trajectories in a RKHS, solving low-rank constraint optimization problems, and exploiting kernel-based computations.

result The proposed algorithm achieves a gain in approximation accuracy and computational efficiency.

reduced modeling non-linear dynamics kernel methods low-rank approximation dynamical systems

2017-10-30abs ↗pdf ↗

Fast approximative estimation of conditional Shapley values when using a linear regression model or a polynomial regression modelstat.ME

Develops fast approximations for conditional Shapley values in linear and polynomial models.

problem Estimating conditional Shapley values using regression models is computationally expensive.

method A new approximative estimation method for conditional Shapley values using linear and polynomial regression models.

result Our method significantly reduces computation time compared to existing methods.

conditional Shapley values linear regression polynomial regression approximation computational efficiency

2025-04-25abs ↗pdf ↗

A Diffusion Approximation for Temporal-Difference Learning with Linear Features under Markovian Noisestat.ML

Stochastic differential equation approximation for linear TD(0) under Markovian noise

problem Temporal-difference learning with linear function approximation

method Stochastic differential equation approximation

result Explains the constant-stepsize error floor

TD learning linear function approximation Markovian noise stochastic differential equation

2026-06-16abs ↗pdf ↗

Piecewise-Linear Approximation for Feature Subset Selection in a Sequential Logit Modelstat.ME

This paper concerns a method of selecting a subset of features for a sequential logit model. Tanaka and Nakagawa (2014) proposed a mixed integer quadratic optimization formulation for solving the problem based on a quadratic approximation of the logistic loss function. However, since there is a significant gap between …

2015-10-19abs ↗pdf ↗

Value Function Approximation in Noisy Environments Using Locally Smoothed Regularized Approximate Linear Programscs.LG

Recently, Petrik et al. demonstrated that L1Regularized Approximate Linear Programming (RALP) could produce value functions and policies which compared favorably to established linear value function approximation techniques like LSPI. RALP's success primarily stems from the ability to solve the feature selection and va…

2012-10-16abs ↗pdf ↗

The distribution of a linear predictor after model selection: Unconditional finite-sample distributions and asymptotic approximationsmath.ST

We analyze the (unconditional) distribution of a linear predictor that is constructed after a data-driven model selection step in a linear regression model. First, we derive the exact finite-sample cumulative distribution function (cdf) of the linear predictor, and a simple approximation to this (complicated) cdf. We t…

2006-11-07abs ↗pdf ↗

Inject Machine Learning into Significance Test for Misspecified Linear Modelscs.LG

Paper presents a machine learning method to improve significance tests for misspecified linear models.

problem Misspecification of linear assumptions in social science models leads to inaccurate significance levels.

method Apply machine learning to fit ground truth function, calculate linear approximation, and adjust the estimator.

result The method significantly outperforms linear regression for non-linear ground truth functions.

machine learning significance test linear approximation misspecified models social science

2020-06-04abs ↗pdf ↗

Development of modeling and control strategies for an approximated Gaussian processstat.ML

A linear model approximates Gaussian processes for efficient control.

problem Efficiently modeling and controlling Gaussian processes with many parameters.

method Developed a linear model using basis functions to approximate Gaussian processes.

result The linear model improves computational efficiency and feasibility of control strategies.

Gaussian process control strategy basis functions efficiency

2020-02-12abs ↗pdf ↗

A Comparative Analysis of Expected and Distributional Reinforcement Learningcs.LG

This paper compares expected and distributional reinforcement learning methods.

problem Understanding why distributional reinforcement learning performs better than expected reinforcement learning.

method Analyzes differences in tabular, linear, and non-linear approximation settings.

result Distributional RL can hurt performance if it does not induce identical behavior.

reinforcement learning distributional RL expected RL tabular linear approximation

2019-01-30abs ↗pdf ↗

Optimal Piecewise Local-Linear Approximationscs.LG

Optimizes piecewise local-linear approximations for global model understanding.

problem Global model behavior interpretation for black-box models.

method Dynamic programming framework for piecewise local-linear approximations with fidelity guarantees.

result Polynomial time algorithm for optimal clustering.

piecewise local-linear black-box model global model behavior fidelity guarantees dynamic programming

2018-06-27abs ↗pdf ↗

Novel and Efficient Approximations for Zero-One Loss of Linear Classifiersstat.ML

This work provides efficient approximations for linear classifiers' performance.

problem Improving the efficiency and accuracy of linear classifiers.

method Developed smooth functions approximating the expected error and ranking loss of linear classifiers, derived from data moments.

result The proposed approximations and optimization algorithms achieve similar or better performance than state-of-the-art methods, significantly faster.

linear classifiers approximations zero-one loss empirical risk minimization smooth functions

2019-02-28abs ↗pdf ↗

Planning to avoid ambiguous states through Gaussian approximations to non-linear sensors in active inference agentseess.SY

Agents learn state ambiguity from non-linear sensor data using Gaussian approximations.

problem Learning state representation from non-linear sensor data.

method Second-order Taylor approximation of Gaussian distribution for non-linear measurement functions.

result Induces a preference for states based on inferability from observations.

active inference robot navigation state ambiguity Gaussian approximation Taylor expansion

2024-09-03abs ↗pdf ↗

Logarithmic Regret for Reinforcement Learning with Linear Function Approximationcs.LG

Logarithmic regret achieved in RL with linear function approximation.

problem Achieving logarithmic regret in reinforcement learning with linear function approximation.

method LSVI-UCB for linear MDP assumption, UCRL-VTR for linear mixture MDP assumption.

result Logarithmic regret bounds established for RL with linear function approximation.

reinforcement learning logarithmic regret linear function approximation linear MDP UCRL-VTR

2020-11-23abs ↗pdf ↗

Measuring Model Complexity of Neural Networks with Curve Activation Functionscs.LG

Paper proposes LANN to measure model complexity of neural networks with curve activation functions.

problem Measuring model complexity of neural networks with curve activation functions.

method Proposes LANN, a piecewise linear framework to approximate curve activation functions, and derives complexity measure based on the number of linear regions.

result Demonstrates positive correlation between overfitting and model complexity during training.

model complexity neural networks curve activation functions LANN overfitting

2020-06-16abs ↗pdf ↗

Provably Correct Optimization and Exploration with Non-linear Policiescs.LG

ENIAC method optimizes and explores complex RL problems with non-linear policies.

problem Theoretical understanding of non-linear policies in RL with strategic exploration.

method ENIAC, an actor-critic method for non-linear function approximation.

result ENIAC finds near-optimal policies in polynomial exploration rounds under bounded eluder dimension.

Reinforcement Learning Policy Optimization Non-linear Function Approximation Strategic Exploration Actor-Critic

2021-03-22abs ↗pdf ↗

Growing axons: greedy learning of neural networks with application to function approximationcs.LG

Greedy method adds neurons one by one for better function approximation.

problem Function approximation in neural networks.

method Growing deep neural network by adding one neuron at a time with non-linear activation.

result Accurate approximants for model problems in function approximation.

neural networks function approximation greedy learning deep learning

2019-10-28abs ↗pdf ↗

Optimism in Reinforcement Learning with Generalized Linear Function Approximationstat.ML

New algorithm reduces reinforcement learning regret to sqrt(d^3T).

problem Efficient reinforcement learning with generalized linear function approximation.

method Optimistic closure assumption for generalized linear functions.

result Proved regret bound of O(sqrt(d^3T)).

reinforcement learning generalized linear models optimism function approximation regret bound

2019-12-09abs ↗pdf ↗

DebiNet: Debiasing Linear Models with Nonlinear Overparameterized Neural Networksstat.ML

DebiNet uses over-parameterized neural networks to improve linear model performance and debiasing.

problem Improving linear model performance and debiasing in high-dimensional settings.

method Incorporates over-parameterized neural networks into semi-parametric models to estimate parameters consistently.

result DebiNet offers valid inference and accurate prediction by leveraging neural networks' universal approximation and linear model's interpretability.

DebiNet over-parameterized neural networks linear models debiasing semi-parametric models

2020-11-01abs ↗pdf ↗

Sample Complexity Characterization for Linear Contextual MDPscs.LG

Paper studies linear CMDPs, improving sample complexity for both models.

problem Improving sample complexity for linear CMDPs.

method Proposes novel model-based algorithms for two linear function approximation models.

result Guaranteed ε-suboptimality gap with desired polynomial sample complexity.

reinforcement learning contextual MDPs linear function approximation sample complexity

2024-02-05abs ↗pdf ↗

Semi-analytic approximate stability selection for correlated data in generalized linear modelsstat.ML

A fast, approximate method for variable selection in GLMs tackles correlated data.

problem Variable selection in generalized linear models with correlated data.

method Replica method of statistical mechanics and vector approximate message passing.

result The proposed algorithm provides fast convergence and high approximation accuracy.

variable selection generalized linear models replica method statistical mechanics vector approximate message passing

2020-03-19abs ↗pdf ↗

Improving predictions of Bayesian neural nets via local linearizationstat.ML

This paper improves Bayesian neural nets by using local linearization.

problem Underfitting in Bayesian neural networks.

method Local linearization of Bayesian neural networks to create a generalized linear model (GLM) for predictions.

result The GLM predictive resolves common underfitting problems of the Laplace approximation.

Bayesian neural networks local linearization underfitting generalized linear model Gaussian process

2020-08-19abs ↗pdf ↗

Designing Universal Causal Deep Learning Models: The Case of Infinite-Dimensional Dynamical Systems from Stochastic Analysismath.DS

The paper introduces Causal Neural Operators to approximate operators in stochastic analysis.

problem Leveraging temporal structure in non-linear operators for deep learning models.

method Designing a deep learning model framework for infinite-dimensional linear metric spaces.

result Causal Neural Operators can uniformly approximate Hölder or smooth trace class operators.

Causal Neural Operators Stochastic Analysis Deep Learning Banach Spaces Temporal Structure

2022-10-24abs ↗pdf ↗

Analytical Approximation for Non-linear FBSDEs with Perturbation Schemeq-fin.CP

In this work, we have presented a simple analytical approximation scheme for generic non-linear FBSDEs. By treating the interested system as the linear decoupled FBSDE perturbed with non-linear generator and feedback terms, we have shown that it is possible to carry out a recursive approximation to an arbitrarily highe…

2011-06-01abs ↗pdf ↗

SurvLIME-Inf: A simplified modification of SurvLIME for explanation of machine learning survival modelscs.LG

SurvLIME-Inf simplifies explanation of survival models using a linear programming approach.

problem Explain complex survival models using simple linear programming.

method Uses

L_{\infty }

-norm for feature importance and explains black-box models.

result SurvLIME-Inf outperforms SurvLIME in small training set scenarios.

Survival analysis Machine learning Explainable AI Linear programming Cox model

2020-05-05abs ↗pdf ↗

SKOLR: Structured Koopman Operator Linear RNN for Time-Series Forecastingcs.LG

SKOLR uses linear RNNs to approximate Koopman operators for time-series forecasting.

problem Nonlinear dynamical system analysis and time-series forecasting with infinite-dimensional Koopman operators.

method Established a connection between Koopman operator approximation and linear RNNs, integrating learnable spectral decomposition and MLP.

result SKOLR delivers exceptional performance in various forecasting benchmarks and dynamical systems.

Koopman operator time-series forecasting Recurrent Neural Networks linear approximation spectral decomposition

2025-06-17abs ↗pdf ↗

Asymptotic Properties of Recursive Maximum Likelihood Estimation in Non-Linear State-Space Modelsmath.ST

The paper analyzes a recursive ML estimation method for non-linear state-space models.

problem Estimating maxima of the log-likelihood function in non-linear state-space models.

method Recursive maximum likelihood estimation using particle approximation to the optimal filter derivative.

result The algorithm accurately estimates maxima of the log-likelihood when the number of particles is sufficiently large.

maximum likelihood non-linear state-space models recursive estimation particle approximation optimal filter derivative

2018-06-25abs ↗pdf ↗

Diffusion Model Based Posterior Sampling for Noisy Linear Inverse Problemscs.LG

A fast method approximates likelihood scores for noisy linear inverse problems.

problem Solving noisy linear inverse problems efficiently.

method Proposes a simple closed-form approximation to the likelihood score for diffusion and flow-based models.

result Significantly faster than baseline methods while maintaining competitive or better reconstruction performances.

diffusion models posterior sampling noisy linear inverse problems fast inference reconstruction

2022-11-20abs ↗pdf ↗

Prior-dependent analysis of posterior sampling reinforcement learning with function approximationstat.ML

Enhances RL with function approximation, improving regret bounds.

problem Improving exploration in reinforcement learning with function approximation.

method Prior-dependent Bayesian regret bound for PSRL with linear mixture MDPs, using value-targeted model learning and variance reduction.

result Established an upper bound of

{\mathcal{O}}(d\sqrt{H^3 T \log T})

for PSRL.

reinforcement learning function approximation PSRL Bayesian regret linear mixture MDPs

2024-03-17abs ↗pdf ↗

Sparse Approximate Solutions to Max-Plus Equations with Application to Multivariate Convex Regressionmath.OC

Efficiently finds sparse solutions to max-plus equations for convex regression.

problem Finding sparse solutions to max-plus equations for convex multivariate regression.

method Polynomial-time algorithm for sparse approximate solutions.

result Optimal piecewise-linear fitting with minimum number of regions.

sparse solutions max-plus equations convex regression polynomial time sparse approximation

2020-11-06abs ↗pdf ↗

Approximation Properties of Variational Bayes for Vector Autoregressionsstat.ML

VB approximates posterior mean perfectly in linear Gaussian VAR models.

problem Unknown approximation error of VB in VAR models.

method Derive approximation error in terms of mean, mode, variance, predictive density, and KL divergence.

result VB approximates posterior mean perfectly.

Variational Bayes Vector Autoregression Bayesian Inference Approximation Error Predictive Density

2019-03-02abs ↗pdf ↗

Scalable Optimal Transport in High Dimensions for Graph Distances, Embedding Alignment, and Morecs.LG

Two log-linear approximations speed up optimal transport for deep learning applications.

problem Computing optimal transport in high dimensions is computationally expensive.

method Locality-sensitive hashing (LSH) and Nyström approximation with LSH-based sparse corrections.

result Log-linear time algorithms for entropy-regularized OT perform well in high-dimensional spaces.

optimal transport log-linear time entropy regularization locality-sensitive hashing Nyström approximation

2021-07-14abs ↗pdf ↗

An Online Prediction Algorithm for Reinforcement Learning with Linear Function Approximation using Cross Entropy Methodcs.LG

New algorithms predict reinforcement learning values efficiently.

problem Predicting reinforcement learning values with linear function approximation.

method Multi-timescale stochastic approximation of cross entropy method.

result Proved convergence and achieved good performance in experiments.

reinforcement learning prediction cross entropy linear function approximation stochastic approximation

2018-06-15abs ↗pdf ↗

On the Curse of Memory in Recurrent Neural Networks: Approximation and Optimization Analysiscs.LG

Study on memory effects in RNNs learning temporal data.

problem Understanding memory effects in RNNs for temporal data learning.

method Mathematical analysis of continuous-time linear RNNs, focusing on approximation and optimization dynamics.

result Long-term memory requires a large number of neurons and slows down training.

Recurrent Neural Networks Temporal Data Memory Effects Approximation Theory Optimization Dynamics

2020-09-16abs ↗pdf ↗

Linear Convergence of Entropy-Regularized Natural Policy Gradient with Linear Function Approximationcs.LG

Entropy-regularized NPG converges linearly with linear function approximation.

problem Analyzing convergence of entropy-regularized NPG with function approximation.

method Established finite-time convergence analyses with entropy regularization and linear function approximation.

result Entropy-regularized NPG achieves linear convergence up to a function approximation error.

entropy regularization natural policy gradient linear function approximation reinforcement learning convergence analysis

2021-06-08abs ↗pdf ↗

Neural Generalized Mixed-Effects Modelsstat.ML

Neural models improve GLMMs for complex data.

problem Nonlinear relationships in grouped data.

method Replaced linear function with neural networks.

result Improved performance on synthetic and real-world data.

Neural Networks Mixed-Effects Models Generalized Linear Models Hierarchical Data Approximate Marginal Likelihood

2026-04-13abs ↗pdf ↗

Cardinality constrained portfolio selection via factor modelsq-fin.PM

Proposes new models to solve portfolio selection with cardinality constraints using factor models.

problem Solving portfolio selection with cardinality constraints using factor models.

method Developed 0-1 linear models and a minimum edge-weighted clique problem to solve the cardinality constrained portfolio problem.

result Piecewise linear approximation reduces computation time for solving the quadratic problem.

portfolio selection cardinality constraints factor models piecewise linear approximation quadratic combinatorial problem

2017-08-08abs ↗pdf ↗

Sparse Multinomial Logistic Regression via Approximate Message Passingcs.IT

For the problem of multi-class linear classification and feature selection, we propose approximate message passing approaches to sparse multinomial logistic regression (MLR). First, we propose two algorithms based on the Hybrid Generalized Approximate Message Passing (HyGAMP) framework: one finds the maximum a posterio…

2015-09-15abs ↗pdf ↗

Going Beyond Linear RL: Sample Efficient Neural Function Approximationcs.LG

This work improves sample efficiency in neural function approximation for reinforcement learning.

problem Improving sample efficiency in reinforcement learning with neural function approximation.

method Study of function approximation with two-layer neural networks (ReLU and polynomial activations) under generative and realizability models.

result Significant improvement in sample complexity compared to linear methods.

Reinforcement Learning Neural Networks Function Approximation Sample Efficiency Two-Layer Networks

2021-07-14abs ↗pdf ↗

Linear Bellman Completeness Suffices for Efficient Online Reinforcement Learning with Few Actionscs.LG

Polynomial-time RL algorithm for constant actions under linear Bellman completeness.

problem Efficient online reinforcement learning with few actions.

method Polynomial-time algorithm based on linear function approximation.

result First computationally efficient algorithm for RL with constant actions under linear Bellman completeness.

reinforcement learning online learning value iteration linear function approximation polynomial-time algorithm

2024-06-17abs ↗pdf ↗

A Finite Sample Analysis of Distributional TD Learning with Linear Function Approximationstat.ML

Study on distributional TD learning with linear approximations for better return estimation.

problem Estimating the return distribution of a policy in reinforcement learning.

method Finite-sample analysis of distributional TD learning with linear function approximation, using the linear-categorical Bellman equation and exponential stability arguments for products of random matrices.

result Sample complexity of linear distributional TD learning matches that of classic linear TD learning, indicating similar difficulty in estimating return distribution versus its expectation.

distributional reinforcement learning temporal difference learning linear function approximation return distribution Markov decision process

2025-02-20abs ↗pdf ↗

Global universality via discrete-time signaturesmath.PR

Global approximation for piecewise linear paths via signatures.

problem Global approximation theorems for piecewise linear paths.

method Using signatures of piecewise linear paths and their density in

L^p

-norms.

result Linear functionals of signatures are dense in

L^p

-norms under an integrability condition.

approximation theory piecewise linear paths signatures Brownian motion random ODEs

2026-03-10abs ↗pdf ↗

Provably Efficient Reinforcement Learning with Linear Function Approximation Under Adaptivity Constraintscs.LG

Efficient RL algorithms for linear function approximation with limited adaptivity constraints.

problem Limited adaptivity in reinforcement learning with linear function approximation.

method Proposed two efficient online RL algorithms for episodic linear Markov decision processes under batch learning and rare policy switch models.

result Achieved efficient regret bounds for both batch learning and rare policy switch models, with substantial reduction in adaptivity.

reinforcement learning linear function approximation adaptivity constraints batch learning rare policy switch

2021-01-06abs ↗pdf ↗

Linear Credit Risk Modelsq-fin.MF

We introduce a novel class of credit risk models in which the drift of the survival process of a firm is a linear function of the factors. The prices of defaultable bonds and credit default swaps (CDS) are linear-rational in the factors. The price of a CDS option can be uniformly approximated by polynomials in the fact…

2016-05-24abs ↗pdf ↗

IKA: Independent Kernel Approximatorcs.LG

IKA approximates kernels with linear combinations of chosen functions, outperforming Nyström method.

problem Efficient kernel approximation for large datasets.

method IKA method approximates kernels as a linear combination of user-defined functions.

result IKA consistently outperformed Nyström method on the STL-10 dataset.

kernel approximation Nyström method linear combination user-defined functions STL-10 dataset

2018-09-05abs ↗pdf ↗

Linear cost and exponentially convergent approximation of Gaussian Matérn processes on intervalsmath.ST

Linear cost method approximates Gaussian Matérn processes with exponentially convergent accuracy.

problem High computational cost for Gaussian process inference and prediction.

method Optimal rational approximation of spectral density for Gaussian processes on bounded intervals.

result Exponential decrease in covariance error with increasing order of approximation.

Gaussian processes Matérn covariance Rational approximation Linear cost Exponential convergence

2024-10-16abs ↗pdf ↗

Ginger: An Efficient Curvature Approximation with Linear Complexity for General Neural Networkscs.LG

Ginger efficiently approximates curvature with linear complexity for neural networks.

problem Quadratic memory and cubic time complexity for computing curvature matrices in deep learning.

method Ginger uses eigendecomposition to maintain the inverse of the generalized Gauss-Newton matrix, achieving linear memory and time complexity.

result Ginger provides an effective and efficient curvature approximation for non-convex objectives.

neural networks curvature approximation linear complexity Gauss-Newton eigendecomposition

2024-02-05abs ↗pdf ↗

Linear predictor on linearly-generated data with missing values: non consistency and solutionscs.LG

Study shows linear predictors fail with missing data, but simpler approximations and neural networks can work.

problem Building predictors with missing data when the target is a linear function of observed data.

method Analyzed the Gaussian case and proposed a linear function of multiway interactions. Studied a simple approximation and proved generalization bounds. Showed multilayer perceptrons with ReLU activation can be consistent.

result Simple approximations and neural networks can be effective in handling missing data, especially with sufficient data.

missing data linear predictors generalization bounds neural networks ReLU activation

2020-02-03abs ↗pdf ↗