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.

168,742 papers · 148 categories

Trend · papers per month

count % of corpus

6 results for “CVXPY”

Optimization for Classical Machine Learning Problems on the GPUcs.LG

Extends GENO framework for GPU optimization of constrained ML problems.

problem Constrained optimization in classical machine learning.

method Extends GENO framework to GPU optimization, specifying problems in a modeling language.

result Solvers on GPU outperform state-of-the-art approaches by several orders of magnitude.

Machine learning Optimization GPU Constrained problems GENO

2022-03-30abs ↗pdf ↗

Differentiable Convex Optimization Layerscs.LG

Differentiable layers for convex optimization problems.

problem Rigidity of existing differentiable optimization layers.

method Disciplined parametrized programming and affine-solver-affine form.

result Efficient analytical differentiation through convex programs.

differentiable optimization convex optimization parametrized programming affine-solver-affine form CVXPY

2019-10-28abs ↗pdf ↗

On Training and Evaluation of Neural Network Approaches for Model Predictive Controlstat.ML

This paper develops a framework for training and evaluating neural networks for MPC.

problem Lack of a general framework for characterizing learning approaches in MPC.

method Developed a framework using PyTorch and CVXPY, incorporating hit-and-run sampling for efficient training data generation.

result Proposed metrics for validating neural network-based MPC approaches.

Model Predictive Control Neural Networks Differentiable Optimization PyTorch CVXPY

2020-05-08abs ↗pdf ↗

Marginal Price Optimizationq-fin.MF

Optimizes AMM markets with a new framework reducing complex optimization to simpler root finding.

problem Optimizing routing and arbitrage in AMM markets.

method Restricts search to boundary of optimal space using marginal prices, reducing high-dimensional optimization to lower-dimensional root finding.

result Significantly faster and more robust performance compared to the original convex optimization method.

AMM markets Optimization Routing Arbitrage Root finding

2025-02-12abs ↗pdf ↗

Physarum Powered Differentiable Linear Programming Layers and Applicationscs.LG

Physarum-inspired solver speeds up LP solving in neural networks.

problem Efficiently solving linear programming problems within neural networks.

method Inspired by Physarum dynamics, a differentiable solver for LPs.

result Solver outperforms existing methods in video segmentation and few-shot learning.

Physarum Linear Programming Deep Learning Meta-Learning Few-Shot Learning

2020-04-30abs ↗pdf ↗

Machine Learning Enhanced Multi-Factor Quantitative Trading: A Cross-Sectional Portfolio Optimization Approach with Bias Correctionq-fin.PM

A new method corrects bias in machine learning for trading by filtering out non-executable prices.

problem Contaminated data from price limits causes misleading performance metrics in trading models.

method Mask-first design with tradability filters, GPU optimization, and penalized losses.

result The system achieves Sharpe ratios of 1.63 on real data, significantly outperforming existing methods.

machine learning quantitative trading portfolio optimization bias correction upstream contamination

2025-06-02abs ↗pdf ↗