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.

169,341 papers · 148 categories

Trend · papers per month

3.3%6.7%10.0%13.3% · Feb 199519922001200920182026
48 results for Nonconvex parametrization

Unified framework for nonconvex matrix completion with linearly parameterized factors.

problem Matrix completion with improved accuracy using linearly parameterized factors.
method Unified nonconvex optimization framework with Correlated Parametric Factorization condition.
result Uniform upper bounds for low-rank estimation at any local minimum.

Geometric insights improve convergence of implicit generative models.

problem Improving convergence of implicit generative models.
method Analyzing geometries induced by Wasserstein distance and other criteria.
result Established surprising approximate global convergence guarantees for the 1-Wasserstein distance.

This paper shows linear over-parametrization suffices for shallow neural networks to fit training data.

problem Training shallow neural networks with optimal over-parametrization.
method Used a simple variant of stochastic gradient descent.
result Linear over-parametrization is sufficient for shallow neural networks to fit training data.

New method reduces over-parametrization in neural networks, ensuring sparsity and finite network size.

problem Over-parametrization leads to too many active neurons in neural networks, especially with large data.
method Investigates a nonconvex regularization method for shallow ReLU networks.
result Locally optimal networks are finite even with infinite data, maintaining approximation guarantees and network size bounds.

Improved zeroth-order algorithms tackle nonconvex minimax problems with reduced complexity.

problem Nonconvex minimax optimization problems in machine learning.
method Design and analysis of Zeroth-Order Gradient Descent Ascent ( exttt{ZO-GDA}) and Zeroth-Order Gradient Descent Multi-Step Ascent ( exttt{ZO-GDMSA}) algorithms.
result Oracle complexity improvements for minimax optimization problems.

The paper optimizes bridge-type estimators for sparse models using pathwise methods.

problem Sparse parametric models with adaptive coefficients and multiple penalties.
method Pathwise optimization with accelerated proximal gradient descent and blockwise alternating optimization.
result Efficient computation of the full solution path for adaptive bridge estimators.

New method improves signal reconstruction with nonconvex penalties and parameter control.

problem Reconstructing sparse signals with nonconvex penalties and nonconvexity control.
method Introduces nonconvex penalties (SCAD, MCP) with nonconvexity parameters and controls them to guide AMP trajectory.
result Achieves perfect reconstruction for relatively dense signals with small nonconvexity parameters.

We study Langevin diffusion for nonconvex functions with manifold structure.

problem Sampling from distributions with nonconvex functions and manifolds of equal probability.
method Prove mixing time bounds for Langevin diffusion using manifold geometry, specialize to matrix factorization problems.
result Langevin diffusion mixes rapidly on manifolds of equal probability in nonconvex functions.

Schedule-free SGD is optimal for nonconvex optimization problems.

problem Nonconvex optimization in neural networks.
method Developed a general framework for online-to-nonconvex conversion, which converts schedule-free SGD into an effective nonconvex optimization algorithm.
result Schedule-free SGD achieves optimal iteration complexity for nonsmooth, nonconvex optimization problems.

PPGD solves nonconvex nonsmooth optimization problems without KL property.

problem Nonconvex and nonsmooth optimization problems in statistics and machine learning.
method Projective Proximal Gradient Descent (PPGD) for solving a class of nonconvex and nonsmooth problems.
result PPGD achieves a fast convergence rate of O(1/k^2) for k ≥ k_0.

New framework explains why nonconvex methods work well in low-rank matrix estimation.

problem Nonconvex low-rank matrix estimation problems in machine learning.
method Developed a theoretical framework revealing a benign regularizer.
result Nonconvex procedures can behave well due to a disguised convexity.

Develops shuffling gradient-based methods for nonconvex-concave minimax optimization.

problem Nonconvex-concave minimax optimization problems.
method Two shuffling gradient-based algorithms for nonconvex-linear and nonconvex-strongly concave settings.
result Achieves state-of-the-art oracle complexity in nonconvex optimization and best-known complexity bounds for nonconvex-strongly concave setting.

New method estimates large covariance matrices using nonconvex penalties.

problem Estimating large covariance matrices in high-dimensional data.
method Developed a first-order algorithm using generalized nonconvex penalties.
result Positive-definite covariance estimators using nonconvex penalties.

Study nonconvex matrix completion for low-rank approximation without rank assumptions.

problem Low-rank approximation of positive semidefinite matrices from partial entries.
method Nonconvex optimization, local-minimum analysis, no spurious local minima.
result Improved sampling rate for nonconvex matrix completion with no spurious local minima.

Paper analyzes fast SAGA method for nonconvex optimization problems.

problem Optimizing nonconvex problems of the form minxifi(x)\min_x \sum_i f_i(x)
method Incremental aggregated gradient method (SAGA) within an Incremental First-order Oracle framework
result SAGA converges to a stationary point faster than gradient descent and stochastic gradient descent, and at a linear rate to the global optimum for a specific class of nonconvex problems.

NESTT tackles nonconvex optimization problems in a distributed and stochastic manner.

problem Nonconvex optimization problems with a sum of nonconvex functions and a nonsmooth regularizer.
method NESTT algorithm that splits the problem into N subproblems and uses an augmented Lagrangian based primal-dual scheme.
result NESTT achieves ε-stationary solution using O((\sum_{i=1}^N\sqrt{L_i/N})^2/ε) gradient evaluations, up to N times better than gradient descent methods.

PGD algorithm converges to local minima in nonconvex matrix completion.

problem Matrix completion with low-rank promotion using nonconvex penalties.
method Proximal gradient descent algorithm for nonconvex penalties.
result PGD algorithm converges to restricted strictly local minimizers with eventually linear rate.

Paper removes bounded gradient assumption for SGD in nonconvex learning.

problem Existing theoretical results for SGD in nonconvex learning require uniform boundedness of gradients, which is hard to verify.
method Establishes sufficient conditions for SGD convergence without bounded gradient assumption.
result SGD achieves optimal convergence rates for nonconvex and gradient-dominated objectives.

This paper establishes lower bounds for smooth nonconvex finite-sum optimization.

problem Understanding the complexity of finding optimal solutions in nonconvex finite-sum optimization.
method Proving tight lower bounds for the complexity of finding ε-suboptimal points and ε-approximate stationary points.
result Existing algorithms achieve optimal IFO complexity up to logarithmic factors.

Paper analyzes convergence of adaptive gradient methods for nonconvex optimization.

problem Lack of convergence guarantees for adaptive gradient methods in nonconvex optimization.
method Fine-grained convergence analysis of adaptive gradient methods including AMSGrad, RMSProp, and AdaGrad.
result Proves adaptive gradient methods converge to first-order stationary points for smooth nonconvex functions.

New algorithm tackles nonconvex machine learning problems with adaptive normalization and independent sampling.

problem Nonconvex machine learning problems with generalized-smoothness.
method Adaptive gradient normalization, independent sampling, and gradient clipping.
result Achieves an O(ε^(-4)) sample complexity for fast convergence.

As surrogate functions of L0L_0-norm, many nonconvex penalty functions have been proposed to enhance the sparse vector recovery. It is easy to extend these nonconvex penalty functions on singular values of a matrix to enhance low-rank matrix recovery. However, different from convex optimization, solving the nonconvex l…

2014-04-29abs ↗pdf ↗

Accelerated SGD method converges linearly to local minima of nonconvex problems.

problem Nonconvex nonsmooth optimization problems.
method Combining variance reduction and Nesterov's extrapolation for accelerated SGD.
result Linear convergence to a stationary point of the nonconvex optimization problem.

Two algorithms solve nonconvex minimax problems with linear constraints, achieving complexity guarantees.

problem Nonconvex minimax problems with coupled linear constraints.
method Zeroth-order primal-dual alternating projected gradient (ZO-PDAPG) and zeroth-order regularized momentum primal-dual projected gradient (ZO-RMPDPG) algorithms.
result Iteration complexity guarantees for solving nonconvex-(strongly) concave minimax problems with coupled linear constraints.

Paper proposes an algorithm to solve complex minimax problems efficiently.

problem Stochastic nonconvex-concave minimax problems in various fields.
method Accelerated first-order regularized momentum descent ascent algorithm (FORMDA).
result Achieves best-known complexity bound of ildeO(ε6.5) ilde{\mathcal{O}}(\varepsilon ^{-6.5}) for single-loop algorithms.