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.

168,657 papers · 148 categories

Trend · papers per month

4118221,2331,644 · Jun 202019922001200920172026
48 results for Differential Machine Learning

Develops a mathematical model for automatic differentiation in machine learning.

problem Current automatic differentiation lacks a simple mathematical model for machine learning.
method Articulates relationships between program differentiation and nonsmooth functions, provides a class of functions and nonsmooth calculus.
result Shows how nonsmooth calculus applies to stochastic approximation methods and evidence of artificial critical points.

Automatic differentiation---the mechanical transformation of numeric computer programs to calculate derivatives efficiently and accurately---dates to the origin of the computer age. Reverse mode automatic differentiation both antedates and generalizes the method of backwards propagation of errors used in machine learni…

2014-04-28abs ↗pdf ↗

Derivatives, mostly in the form of gradients and Hessians, are ubiquitous in machine learning. Automatic differentiation (AD), also called algorithmic differentiation or simply "autodiff", is a family of techniques similar to but more general than backpropagation for efficiently and accurately evaluating derivatives of…

2015-02-20abs ↗pdf ↗

Mathematical framework for differential machine learning in finance.

problem Theoretical assumptions in financial models and their impact on machine learning algorithms.
method Rigorous mathematical framework for differential machine learning in finance.
result Theoretical grounding enhances the predictive capabilities of neural networks in financial applications.

Gradient sparsification enhances privacy-preserving machine learning models.

problem Improving performance of differentially-private machine learning models under privacy constraints.
method Gradient sparsification combined with compressed sensing and additive Laplace noise.
result Gradient sparsification can improve performance of differentially-private machine learning models for small privacy budgets.

Defines a calculus for integrating Moreau envelopes in differentiable programming.

problem Lack of a mathematical framework for applying Moreau envelopes to deep networks and machine learning systems.
method Develops a compositional calculus adapted to Moreau envelopes and integrates it into differentiable programming.
result Integrates Moreau envelopes into differentiable programming, enabling new gradient back-propagation methods.

Differential ML combines AAD with ML for fast, accurate financial derivatives pricing and risk management.

problem Computational bottlenecks in financial derivatives risk management.
method Novel algorithms using automatic adjoint differentiation (AAD) for training fast, accurate approximations in real-time.
result Convergence guarantees for fast, accurate pricing and risk approximations for arbitrary derivatives instruments.

AD-EnKFs use machine learning to improve data assimilation in high-dimensional systems.

problem Data assimilation in high-dimensional, unknown dynamics systems.
method Auto-differentiable ensemble Kalman filters blending machine learning and ensemble Kalman filters.
result AD-EnKFs outperform existing methods in the Lorenz-96 model.

Automated hyperparameter tuning aspires to facilitate the application of machine learning for non-experts. In the literature, different optimization approaches are applied for that purpose. This paper investigates the performance of Differential Evolution for tuning hyperparameters of supervised learning algorithms for…

2019-04-15abs ↗pdf ↗

Elvet solves differential equations and variational problems with neural networks.

problem Solving complex differential and variational equations with arbitrary conditions.
method Machine learning, specifically neural networks, to represent and solve equations.
result Elvet can solve a wide range of differential and variational problems.

Automates feature extraction from JSON data for machine learning.

problem Manual feature engineering for JSON data is laborious, lossy, and prone to bias.
method Automates feature extraction using Mill.jl and JsonGrinder.jl.
result Creates a differentiable machine learning model from raw JSON samples.

Traditional differential privacy is independent of the data distribution. However, this is not well-matched with the modern machine learning context, where models are trained on specific data. As a result, achieving meaningful privacy guarantees in ML often excessively reduces accuracy. We propose Bayesian differential…

2019-01-28abs ↗pdf ↗

This paper addresses privacy concerns in ratio statistics using differential privacy.

problem Privacy concerns in ratio statistics across machine learning areas.
method Develops a simple algorithm for differentially private ratio statistics, proving consistency and constructing confidence intervals.
result A simple algorithm can provide excellent privacy, sample accuracy, and bias properties in ratio statistics.

Extends machine learning models for analytic boundary conditions in differential equations.

problem Inclusion of data in differential equations using symbolic algorithms.
method Combines computer algebra with Gaussian processes and extends to analytic boundary conditions using Gröbner and Janet bases of Weyl algebras.
result Describes divergence-free flow in domains bounded by analytic functions.

Differentiable EM for Gaussian Mixture Models improves model integration.

problem Non-differentiability of EM algorithm limits its use in modern learning pipelines.
method Presented and compared several differentiation strategies for EM.
result Differentiable EM enables the use of Mixture Wasserstein distance in machine learning tasks.

This paper benchmarks privacy-preserving machine learning on medical images.

problem Ensuring privacy in medical image analysis while maintaining model accuracy.
method Comparing Local-DP and DP-SGD for differential privacy in medical imagery.
result Theoretical privacy guarantees do not fully align with real-world performance.

Sherpa.ai framework combines federated learning and differential privacy for edge AI services.

problem Protecting data privacy in edge AI services.
method Holistic federated learning and differential privacy approach with methodological guidelines.
result Demonstrated through classification and regression use cases.

Alternating Direction Method of Multipliers (ADMM) is a widely used tool for machine learning in distributed settings, where a machine learning model is trained over distributed data sources through an interactive process of local computation and message passing. Such an iterative process could cause privacy concerns o…

2018-08-30abs ↗pdf ↗

Differentially private learning on real-world data poses challenges for standard machine learning practice: privacy guarantees are difficult to interpret, hyperparameter tuning on private data reduces the privacy budget, and ad-hoc privacy attacks are often required to test model privacy. We introduce three tools to ma…

2018-12-07abs ↗pdf ↗

Differentially private hyperparameter tuning improves privacy in machine learning.

problem Hyperparameter tuning leaks private information through selected configurations.
method Local Bayesian optimization using Gaussian Process surrogate for private gradient approximation.
result DP-GIBO converges to locally optimal hyperparameters with polynomial dimensional dependence.

This article introduces machine learning methods for solving PDEs.

problem Approximating solutions of partial differential equations.
method Machine learning methods, including physics-informed neural networks and deep operator learning.
result Recent advances in machine learning have made PDE solutions more accessible.

Due to massive amounts of data distributed across multiple locations, distributed machine learning has attracted a lot of research interests. Alternating Direction Method of Multipliers (ADMM) is a powerful method of designing distributed machine learning algorithm, whereby each agent computes over local datasets and e…

2019-01-07abs ↗pdf ↗

Publicly pretraining models on Web data may undermine differential privacy.

problem The use of large Web-scraped datasets in differential privacy models.
method Critical review of leveraging pretrained models on public datasets for differential privacy.
result Publicizing pretrained models as 'private' could harm trust and generalize poorly.

EXAGREE selects a stakeholder-aligned model to reduce conflicting explanations in machine learning.

problem Conflicting explanations from different attribution methods limit the adoption of machine learning models in safety-critical domains.
method EXAGREE is a two-stage framework that selects a Stakeholder-Aligned Explanation Model (SAEM) from a set of similar-performing models, maximizing Stakeholder-Machine Agreement (SMA).
result EXAGREE achieves simultaneous gains in faithfulness, plausibility, and fairness over baselines while preserving task accuracy.

One-pass private sketch supports various machine learning tasks.

problem Efficiently supporting multiple machine learning tasks with differential privacy.
method Randomized contingency tables indexed with locality-sensitive hashing, constructed in one pass.
result Competitive error bounds for DP kernel density estimation, faster than existing methods.

Differentially private algorithms protect model explanations from leaking training data.

problem Model explanations can leak training data, compromising privacy.
method Adaptive differentially private gradient descent algorithm to produce accurate, private explanations.
result Privacy amplification and reduction of overall privacy loss on explanation data.

Extends batch active learning to non-differentiable models.

problem Efficiently training machine learning models on large, initially unlabelled datasets.
method Black-box batch active learning for regression tasks that relies solely on model predictions.
result Achieves strong performance on regression datasets compared to white-box approaches for deep learning models.

Deep fictitious play converges to Nash equilibrium in stochastic differential games.

problem Finding Nash equilibrium in large stochastic differential games.
method Decouples the game into sub-optimization problems and solves each player's optimal strategy with deep BSDE method.
result Deep fictitious play converges to the true Nash equilibrium.

Quantum machine learning solves high-dimensional PDEs with lower variance and improved accuracy.

problem Approximating solutions to high-dimensional parabolic PDEs.
method Pure Variational Quantum Circuit (VQC) for BSDE approximation, using temporal discretization and Monte Carlo simulation.
result VQC achieves lower variance and improved accuracy in most cases, particularly in highly nonlinear regimes.

New method reduces privacy impact on model accuracy for underrepresented groups.

problem Privacy mechanisms disproportionately affect underrepresented groups in machine learning models.
method Proposes DPSGD-F, a modified DPSGD that adjusts group contributions based on clipping bias.
result DPSGD-F removes disparate impact of differential privacy on model accuracy for protected groups.