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

4118221,2321,643 · Jun 202019922001200920182026
48 results for generalized linear problems

Analyzes generalization error in generalized linear models, explaining double descent phenomenon.

problem Understanding generalization of machine learning models in high dimensions.
method Develops a framework to characterize asymptotic generalization error for generalized linear models.
result Rigorously explains the double descent phenomenon in generalized linear models.

New algorithm for identifying best drug arm in generalized linear bandits.

problem Identifying the best drug arm in drug design with minimal trials.
method Proposes an algorithm for best-arm identification in generalized linear bandits, providing theoretical guarantees and simulations.
result First algorithm for best-arm identification in generalized linear bandits with theoretical guarantees.

MCGDiff uses SGM to guide SMC for solving ill-posed linear inverse problems.

problem Solving ill-posed linear inverse problems in Bayesian settings.
method Exploiting SGM structure, defining a sequence of intermediate problems, and using SMC methods.
result MCGDiff outperforms competing methods in Bayesian ill-posed inverse problems.

New method solves large-scale linear programming problems for sparse signal reconstruction.

problem Efficiently solving large-scale linear programming problems for sparse signal reconstruction.
method Combining constraint and column generation techniques with simplex method initialization.
result Highly efficient solutions for many settings.

Efficiently approximates population risk in large-scale generalized linear problems.

problem Computational intractability of minimizing empirical risk in large-scale settings.
method Designing an efficient algorithm that approximates the population risk minimizer in generalized linear problems.
result Achieves the same accuracy as empirical risk minimizer through cheaper iterations with cubic convergence rate.

New method for estimating parameters in inverse problems using double robustness.

problem Estimating parameters defined as linear functionals of solutions to linear inverse problems.
method Source condition double robust inference method that uses iterated Tikhonov regularized adversarial estimators.
result Asymptotic normality of the parameter of interest as long as either the primal or dual inverse problem is sufficiently well-posed.

Neural networks enhance linear programming for complex decision-making problems.

problem High-dimensional and combinatorial operations research problems.
method Hybrid solution method combining linear programming and neural networks.
result Neural network value function approximations outperform polynomial approximations in a transportation problem.

Differentiable cutting-plane layers solve parametric mixed-integer linear optimization problems.

problem Solving parametric mixed-integer linear optimization problems with changing data.
method Introducing cutting-plane layers (CPLs) for differentiable cutting-plane generation.
result The algorithm computes solutions with low integrality gaps and generalizes to unseen instances.

New classifier combines locally linear kernels for fast and accurate non-linear classification.

problem Developing a fast and accurate non-linear classifier.
method Combines locally linear classifiers using a 1\ell_1 Multiple Kernel Learning (MKL) problem with scalable MKL training for streaming kernels.
result The resulting classifier achieves high accuracy with fast inference time.

Gradient EM converges exponentially to optimal solution in agnostic mixtures.

problem Fitting kk parametric functions to given data points without a generative model.
method Gradient EM algorithm for agnostic mixtures of arbitrary parametric functions.
result Gradient EM converges exponentially to population loss minimizers with high probability.

The MEM method uses data-driven priors for linear inverse problems, proving convergence and estimating differences.

problem Linear inverse problems with approximate priors.
method Maximum Entropy on the Mean (MEM) method with data-driven priors.
result Empirical mean convergence and estimates for prior differences based on epigraphical distance.

New algorithm uses GANs to solve linear inverse problems with theoretical guarantees.

problem Solving linear inverse problems with natural signals and images.
method Proposes a PGD algorithm using GAN priors for linear inverse problems.
result Demonstrates superior performance over existing GAN-based methods for compressive sensing.

We present an efficient algorithm for simultaneously training sparse generalized linear models across many related problems, which may arise from bootstrapping, cross-validation and nonparametric permutation testing. Our approach leverages the redundancies across problems to obtain significant computational improvement…

2013-07-31abs ↗pdf ↗

Study solves inverse problems for equations with fractional nonlinearities.

problem Solving inverse problems for semilinear elliptic equations with fractional power nonlinearities.
method Higher order linearization method adapted for fractional order.
result Results of previous studies remain valid for general power nonlinearities.

Paper analyzes agnostic learning of mixed linear regression without generative models.

problem Learning mixed linear regression without assuming stochastic generation.
method Expectation Maximization (EM) and Alternating Minimization (AM) algorithms.
result AM and EM algorithms converge to population loss minimizers under standard conditions.

Study non-linear combinatorial bandits with polynomial rewards, finding significant differences from linear cases.

problem Adversarial combinatorial bandits with general non-linear reward functions.
method Extending existing work on adversarial linear combinatorial bandits, analyzing minimax optimal regret for polynomial and non-polynomial reward functions.
result Minimax optimal regret bounds for adversarial combinatorial bandits with general non-linear reward functions.

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.

Proves formula for reconstruction performance in generalized linear models.

problem Analyzing reconstruction performance in generalized linear models with arbitrary bounded spectrum.
method Message passing algorithms and dynamical system stability analysis.
result Analytical formula confirms replica method conjecture for convex models.

The paper finds the extremal compatible linear connection on generalized Berwald manifolds.

problem Finding the extremal compatible linear connection on generalized Berwald manifolds.
method Minimizing the pointwise length of the torsion tensor, solving conditional extremum problems.
result An intrinsic algorithm to check the existence of compatible linear connections on Finsler manifolds.

New method uses diffusion models for Bayesian inverse problems.

problem Solving Bayesian inverse problems with linear-Gaussian models.
method Decoupled Diffusion Sequential Monte Carlo (DDSMC) method.
result Asymptotically exact solution demonstrated on various data types.

The paper provides a non-asymptotic error bound for linear system identification under nonlinear policies.

problem System identification for linear systems with nonlinear and/or time-varying policies under i.i.d. random excitation noises.
method Least square estimation with non-asymptotic error bound for bounded state and action trajectories.
result The error bound is consistent with linear policies and generalizes existing guarantees.

The SPS method constructs confidence regions for true parameters with optimal sample complexity.

problem Constructing exact, non-asymptotic confidence regions for true system parameters.
method Sign-Perturbed Sums (SPS) method, generalized to various types of problems.
result High probability upper bounds for SPS confidence regions show optimal shrinkage rate.

The paper improves SVR with linear constraints for better model properties.

problem Improving Support Vector Regression with linear constraints.
method Generalized SMO algorithm for solving optimization with linear constraints.
result The proposed method shows better practical performance on various datasets.

The affine Grassmannian generalizes Euclidean and linear subspaces with rich geometric properties.

problem Formulating machine learning and statistical problems on the affine Grassmannian.
method Showed the affine Grassmannian has multiple structures and affords an analogue of Schubert calculus.
result The affine Grassmannian serves as a concrete computational platform for various machine learning and statistical problems.

Unified approach for optimizing predictions in linear programming and inverse problems.

problem Optimizing predictions in linear programming and inverse problems.
method Maximum optimality margin approach.
result Unified approach that balances computational efficiency and theoretical properties.

Motivated by Pan-Yang [PY] and Ma-Cheng [MC], we study a general linear nonlocal curvature flow for convex closed plane curves and discuss the short time existence and asymptotic convergence behavior of the flow. Due to the linear structure of the flow, this partial differential equation problem can be resolved using a…

2010-12-01abs ↗pdf ↗

Distributed algorithm for fitting generalized linear models with regularization.

problem Training large-scale generalized linear models with regularization in distributed environments.
method Distributed coordinate descent with line search, addressing slow node problem.
result Our approach is scalable and superior for training on large and sparse datasets.

ICE algorithm solves exact 0-1 loss linear classification problem efficiently.

problem Exact solution to the 0-1 loss linear classification problem for non-linearly separable data.
method Incremental cell enumeration (ICE) algorithm, leveraging combinatorial and incidence relations.
result First provably optimal algorithm for exact 0-1 loss linear classification problem.