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.

168,695 papers · 148 categories

Trend · papers per month

count % of corpus

48 results for “Non-linear Optimization”

Non-Linear Counterfactual Aggregate Optimizationstat.ML

Optimizes non-linear outcomes from summed contributions.

problem Maximizing a non-linear function of summed small contributions.

method Derives a scalable descent algorithm leveraging concentration properties.

result Directly optimizes for stated objective, e.g., A/B test success criterion.

non-linear optimization sum of contributions concentration properties A/B testing counterfactuals

2025-09-03abs ↗pdf ↗

Statistical Complexity and Optimal Algorithms for Non-linear Ridge Banditsstat.ML

Optimal algorithms for non-linear ridge bandits reduce burn-in cost.

problem Non-linear models introduce a burn-in period with fixed cost.

method Two-stage algorithm: find initial action, then treat locally linear.

result Two-stage algorithm is statistically optimal.

non-linear ridge bandits burn-in period statistical optimality two-stage algorithm

2023-02-12abs ↗pdf ↗

Non-linear shrinkage of the price return covariance matrix is far from optimal for portfolio optimisationq-fin.PM

Non-linear shrinkage isn't optimal for portfolio optimization, especially when asset dependence is non-stationary.

problem Optimizing portfolios with non-stationary asset dependence structures.

method Derived and compared non-linear shrinkage with an optimal target for covariance matrix estimation.

result Non-linear shrinkage can be significantly improved for portfolio optimization.

portfolio optimization covariance matrix non-linear shrinkage non-stationary dependence Oracle eigenvalues

2021-12-14abs ↗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 ↗

Optimal Stopping for Non-linear Expectationsmath.OC

We develop a theory for solving continuous time optimal stopping problems for non-linear expectations. Our motivation is to consider problems in which the stopper uses risk measures to evaluate future rewards.

2009-05-22abs ↗pdf ↗

Adversarial Combinatorial Bandits with General Non-linear Reward Functionsstat.ML

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.

Adversarial Bandits Non-Linear Reward Polynomial Reward Regret Analysis Combinatorial Optimization

2021-01-05abs ↗pdf ↗

Unfolding recurrence by Green's functions for optimized reservoir computingcond-mat.dis-nn

This work optimizes reservoir computing models by linking recurrence and non-linear dynamics.

problem Understanding how recurrence and non-linear dynamics in cortical networks contribute to their function.

method Transformed time-continuous, recurrent dynamics into an effective feed-forward structure of linear and non-linear temporal kernels.

result Optimal time-series classifiers can be built from random reservoir networks, demonstrating significant performance gains.

reservoir computing recurrence non-linear dynamics cortical networks feed-forward networks

2020-10-13abs ↗pdf ↗

From Alexnet to Transformers: Measuring the Non-linearity of Deep Neural Networks with Affine Optimal Transportcs.LG

Paper introduces non-linearity signature to measure deep neural network performance.

problem Difficulty in explaining performance differences among similar DNN architectures.

method Affine Optimal Transport mappings to measure non-linearity.

result Signature provides better understanding of DNN inner workings.

Deep Neural Networks Non-linearity Optimal Transport Affine Opt Computer Vision

2023-10-17abs ↗pdf ↗

Some Computations for Optimal Execution with Monotone Strategiesq-fin.MF

Study optimal execution in financial markets with constraints.

problem Optimal execution with non-negative constraints in a linear price impact model.

method Purely probabilistic approach via non-linear ODE.

result Complete characterization of value and optimal control.

Optimal Execution Monotone Strategies Black-Scholes Model Non-negative Constraints Linear Price Impact

2024-11-16abs ↗pdf ↗

Quantum speedup of non-linear Monte Carlo problemsquant-ph

Quantum computing offers a quadratic speedup for estimating non-linear functionals.

problem Estimating non-linear functionals of probability distributions.

method Proposes a quantum-inside-quantum Monte Carlo algorithm for a broad class of non-linear estimation problems.

result Achieves a quadratic speedup for non-linear estimation problems, including nested conditional expectations and stochastic optimization.

quantum computing Monte Carlo methods non-linear functionals probability distributions nested conditional expectations

2025-02-07abs ↗pdf ↗

Fundamental limits of Non-Linear Low-Rank Matrix Estimationstat.ML

Paper establishes limits for accurately estimating low-rank matrices from noisy, non-linear data.

problem Estimating low-rank matrices from noisy, non-linear observations.

method Proves strong universality result with equivalent Gaussian model and effective prior parameters.

result Signal-to-noise ratio requirement grows as $N^{rac 12 (1-1/k_F)}$ for accurate reconstruction.

Matrix Estimation Low-Rank Non-Linear Bayes Optimal Signal-to-Noise Ratio

2024-03-07abs ↗pdf ↗

Regression with Deep Learning for Sensor Performance Optimizationeess.SP

Deep learning improves sensor performance optimization.

problem Optimizing sensor performance based on key metrics.

method Re-approach non-linear regression using deep learning with Keras and Tensorflow.

result Deep learning models improve sensor performance optimization.

deep learning sensor performance non-linear regression Tensorflow Keras

2020-02-22abs ↗pdf ↗

Optimizing Generalized Rate Metrics through Game Equilibriumcs.LG

We present a general framework for solving a large class of learning problems with non-linear functions of classification rates. This includes problems where one wishes to optimize a non-decomposable performance metric such as the F-measure or G-mean, and constrained training problems where the classifier needs to sati…

2019-09-06abs ↗pdf ↗

Non-linear ICA based on Cramer-Wold metriccs.LG

Non-linear source separation is a challenging open problem with many applications. We extend a recently proposed Adversarial Non-linear ICA (ANICA) model, and introduce Cramer-Wold ICA (CW-ICA). In contrast to ANICA we use a simple, closed--form optimization target instead of a discriminator--based independence measure…

2019-03-01abs ↗pdf ↗

Inference-Aware Meta-Alignment of LLMs via Non-Linear GRPOstat.ML

Inference-aware meta-alignment of LLMs reduces computational cost.

problem Aligning LLMs to diverse human preferences is challenging due to conflicting criteria.

method IAMA trains a base model to be aligned to multiple tasks via different inference-time alignment algorithms, using non-linear GRPO for optimization.

result IAMA enables effective alignment of LLMs to multiple criteria with limited computational budget.

LLMs alignment inference-time non-linear optimization probability measures

2026-02-02abs ↗pdf ↗

Mean-field underdamped Langevin dynamics and its spacetime discretizationstat.CO

New method optimizes non-linear functionals over probability measures.

problem Optimizing non-linear functionals defined over probability measures.

method N-particle underdamped Langevin algorithm with spacetime discretization.

result Converges globally in total variation distance.

mean-field underdamped Langevin probability measures non-linear functionals optimization

2023-12-26abs ↗pdf ↗

Optimal Liquidation of Perpetual Contractsq-fin.MF

Agent optimizes perpetual contract liquidation with transaction costs and risk.

problem Optimizing perpetual contract liquidation with transaction costs and risk.

method Solving stochastic control problem for optimal trading strategy.

result Closed-form expression and approximations for optimal strategy.

Perpetual Contracts Optimal Liquidation Transaction Costs Stochastic Control Funding Rate

2026-01-15abs ↗pdf ↗

Loss landscapes and optimization in over-parameterized non-linear systems and neural networkscs.LG

This work proposes a mathematical framework for loss landscapes and optimization in deep neural networks.

problem The effectiveness of gradient-based optimization in over-parameterized neural networks.

method A modern view and mathematical framework of loss landscapes and efficient optimization in over-parameterized machine learning models.

result Wide neural networks satisfy the PL

^*

condition, explaining (S)GD convergence to a global minimum.

deep learning neural networks loss landscapes optimization gradient descent

2020-02-29abs ↗pdf ↗

Non-linear non-zero-sum Dynkin games with Bermudan strategiesmath.OC

Study Nash equilibrium in non-zero-sum game with Bermudan strategies.

problem Optimizing pay-offs in non-linear non-zero-sum games.

method Recursive construction to find Nash equilibrium.

result Existence of Nash equilibrium in non-zero-sum game.

Nash equilibrium non-zero-sum game Bermudan strategies recursive construction non-linear assessment functional

2023-11-02abs ↗pdf ↗

LQF: Linear Quadratic Fine-Tuningcs.LG

LQF linearizes deep models for better interpretability.

problem Lack of interpretability in deep neural networks.

method Simple modifications to architecture, loss function, and optimization.

result Comparable performance to non-linear fine-tuning, with interpretability.

linear models deep learning interpretability Kronecker factorization Leaky-ReLU

2020-12-21abs ↗pdf ↗

O(1/k)

Finite-Time Bound for Non-Linear Two-Time-Scale Stochastic Approximationcs.LG

Improved bounds for non-linear SA with fast convergence.

problem Stochastic approximation with non-linear mappings and multiple time scales.

method Mean squared error bounds with

O(1/k)

rate for contractive mappings.

result First

O(1/k)

rate for non-linear two-time-scale SA without additional smoothness assumptions.

stochastic approximation two-time-scale non-linear mean squared error contractive mappings

2025-04-27abs ↗pdf ↗

Multiple Locally Linear Kernel Machinescs.LG

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

\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.

Locally Linear Classifiers Multiple Kernel Learning Non-linear Classification Scalable Algorithms Fast Inference

2024-01-17abs ↗pdf ↗

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

Using stochastic gradient search and the optimal filter derivative, it is possible to perform recursive (i.e., online) maximum likelihood estimation in a non-linear state-space model. As the optimal filter and its derivative are analytically intractable for such a model, they need to be approximated numerically. In [Po…

2018-06-25abs ↗pdf ↗

On the Optimality of Nuclear-norm-based Matrix Completion for Problems with Smooth Non-linear Structuremath.ST

Matrix completion works well for smooth non-linear structures, even without low-rank assumptions.

problem Matrix completion for smooth non-linear structures.

method Nuclear-norm penalization for matrices lying in a low-dimensional non-linear manifold.

result Nuclear-norm penalization is minimax rate optimal for recovering smooth non-linear matrices with missing data.

matrix completion nuclear norm non-linear manifold smooth function missing data

2021-05-05abs ↗pdf ↗

Enjoying Non-linearity in Multinomial Logistic Bandits: A Minimax-Optimal Algorithmstat.ML

Improved regret bound for multinomial logistic bandits with non-linearity.

problem Maximizing rewards in multinomial logistic bandits with non-linear feedback.

method Extended the definition of

κ_*

to multinomial setting and proposed an efficient algorithm.

result Minimax-optimal regret bound of

\smash{\widetilde{\mathcal{O}}( R d \sqrt{ {KT}/{κ_*}} ) }

, improving over existing guarantees.

bandits logistic non-linearity minimax recommender systems

2025-07-07abs ↗pdf ↗

Instance-Wise Minimax-Optimal Algorithms for Logistic Banditscs.LG

Improved algorithm for logistic bandits with better regret bounds.

problem Understanding the impact of non-linearity in logistic bandits.

method Introducing a new algorithm and providing refined analysis.

result Improved regret bounds scaling as

\tilde{\mathcal{O}}(d\sqrt{T/κ})

in most favorable cases.

Logistic Bandits Non-linearity Minimax-Optimal Regret Bounds Exploration-Exploitation

2020-10-23abs ↗pdf ↗

Pessimistic Nonlinear Least-Squares Value Iteration for Offline Reinforcement Learningcs.LG

Papers learn from data to make decisions without interacting, improving on previous methods.

problem Achieving optimal decision-making from offline data with non-linear function approximation.

method Pessimistic Nonlinear Least-Square Value Iteration (PNLSVI) with three innovative components.

result Achieves minimax optimal instance-dependent regret for non-linear function approximation.

offline reinforcement learning non-linear function approximation value iteration regret bound minimax optimality

2023-10-02abs ↗pdf ↗

A comparison of linear and non-linear calibrations for speaker recognitionstat.ML

In recent work on both generative and discriminative score to log-likelihood-ratio calibration, it was shown that linear transforms give good accuracy only for a limited range of operating points. Moreover, these methods required tailoring of the calibration training objective functions in order to target the desired r…

2014-02-11abs ↗pdf ↗

Taming the Interacting Particle Langevin Algorithm: The Superlinear casemath.PR

New algorithm tames non-linear growth in stochastic optimization.

problem Computational challenges in E-step of EM framework.

method Employing interacting particle systems and taming techniques to create tIPLA.

result Non-asymptotic convergence error estimates in Wasserstein-2 distance for tIPLA.

stochastic optimization IPS EM framework tamed IPLA non-linear growth

2024-03-28abs ↗pdf ↗

The CMA Evolution Strategy: A Tutorialcs.LG

This tutorial introduces the CMA Evolution Strategy (ES), where CMA stands for Covariance Matrix Adaptation. The CMA-ES is a stochastic, or randomized, method for real-parameter (continuous domain) optimization of non-linear, non-convex functions. We try to motivate and derive the algorithm from intuitive concepts and …

2016-04-04abs ↗pdf ↗

Riemannian Archetypal Analysis: Interpretable non-linear data analysis on deformed star distributionscs.LG

Develops a Riemannian archetypal analysis for interpretable non-linear data.

problem Limited performance of classical archetypal analysis on non-linear data.

method Riemannian geometry for data-driven pullback, geodesic convex combinations, convex relaxation followed by non-convex refinement.

result Combines interpretability of classical archetypal analysis with expressive power of modern non-linear models.

archetypal analysis non-linear data Riemannian geometry deformed star distributions geodesic convex combinations

2026-05-22abs ↗pdf ↗

Convergence analysis of Tikhonov regularization for non-linear statistical inverse learning problemsmath.ST

We study a non-linear statistical inverse learning problem, where we observe the noisy image of a quantity through a non-linear operator at some random design points. We consider the widely used Tikhonov regularization (or method of regularization, MOR) approach to reconstruct the estimator of the quantity for the non-…

2019-02-14abs ↗pdf ↗

Bias-Robust Bayesian Optimization via Dueling Banditsstat.ML

Bayesian optimization improved for biased data.

problem Adversarial bias in observations, especially hidden confounders.

method Reduction to dueling bandits, information-directed sampling (IDS).

result First efficient kernelized algorithm with regret guarantees.

Bayesian optimization dueling bandits information-directed sampling cumulative regret kernelized algorithms

2021-05-25abs ↗pdf ↗

DART: aDaptive Accept RejecT for non-linear top-K subset identificationcs.LG

DART optimizes subset selection in non-linear bandit problems.

problem Optimizing subset selection in non-linear bandit problems with correlated rewards.

method DART algorithm for combinatorial bandits without individual arm feedback or linearity assumption.

result DART achieves a regret bound of

ilde{\mathcal{O}}(K\sqrt{KNT})

bandit problem subset selection non-linear rewards adaptive rejection cross-selling optimization

2020-11-16abs ↗pdf ↗

Near-optimal Offline and Streaming Algorithms for Learning Non-Linear Dynamical Systemscs.LG

We develop algorithms to learn non-linear dynamical systems without mixing assumptions.

problem Learning non-linear dynamical systems from dependent data.

method We introduce an offline algorithm and a one-pass streaming method with SGD-RER.

result Our methods achieve optimal or near-optimal performance for learning non-linear systems.

non-linear dynamical systems learning algorithms dependent data mixing assumption SGD-RER

2021-05-24abs ↗pdf ↗

Non-linear Functional Modeling using Neural Networkscs.LG

New neural network models for functional data.

problem Handling non-linear functional data.

method Functional Direct Neural Network (FDNN) and Functional Basis Neural Network (FBNN) with gradient-based optimization.

result Demonstrated effectiveness in complex functional models.

neural networks functional data non-linear modeling gradient descent basis expansions

2021-04-19abs ↗pdf ↗

Suboptimality of Constrained Least Squares and Improvements via Non-Linear Predictorsmath.ST

Least squares estimator fails to achieve optimal risk in bounded distributions, but non-linear predictors can.

problem Optimal risk in bounded distributions for constrained least squares.

method Comparison of least squares and non-linear predictors.

result Non-linear predictors can achieve optimal risk

O(d/n)

in bounded distributions.

least squares non-linear predictors bounded distributions excess risk optimal rate

2020-09-19abs ↗pdf ↗

Off-the-grid learning of mixtures from a continuous dictionarystat.ML

Method estimates mixture components without discretizing parameters.

problem Learning from mixtures of continuous features with noise.

method Off-the-grid optimization method for continuous parameter space.

result Prediction error bound similar to Lasso predictor.

mixture models continuous dictionary off-the-grid optimization prediction error Gaussian noise

2022-06-29abs ↗pdf ↗

Minimizing False-Positive Attributions in Explanations of Non-Linear Modelscs.LG

PatternLocal improves XAI for non-linear models by suppressing suppressor variables.

problem Suppressor variables cause false-positive feature attributions in non-linear models.

method PatternLocal uses locally linear surrogate models and transforms weights into a generative representation.

result PatternLocal reduces false-positive attributions and provides more reliable explanations.

XAI Non-linear models Suppressor variables False-positive Local fidelity

2025-05-16abs ↗pdf ↗

Learning to Estimate Without Biascs.LG

Paper proposes a bias-constrained deep learning approach to non-linear estimation.

problem Designing unbiased estimators for non-linear models.

method Bias Constrained Estimator (BCE) using deep learning with bias constraints.

result Asymptotic MVUEs with Cramer Rao bound performance.

Bias Constrained Estimator Deep Learning Non-Linear Estimation Cramer Rao Bound Signal to Noise Ratio

2021-10-24abs ↗pdf ↗

Forecast reconciliation with non-linear constraintsstat.ME

This paper extends forecast reconciliation to non-linearly constrained time series.

problem Forecasting time series with non-linear constraints.

method Non-linearly Constrained Reconciliation (NLCR) algorithm that adjusts forecasts to meet non-linear constraints.

result NLCR significantly improves forecast accuracy compared to benchmarks.

forecast reconciliation non-linear constraints optimization time series forecasting demography

2025-10-24abs ↗pdf ↗

Randomized Signature Methods in Optimal Portfolio Selectionq-fin.PM

Empirical study shows Randomized Signature Methods improve portfolio optimization in financial markets.

problem Drift estimation in non-linear, non-parametric financial markets is challenging.

method Applied Randomized Signature Methods for non-linear, non-parametric drift estimation in multi-variate financial markets.

result Randomized Signature Methods provide features on the same scale and improve portfolio optimization in real-world settings.

Randomized Signatures Portfolio Optimization Financial Markets Drift Estimation Non-Parametric

2023-12-27abs ↗pdf ↗

Non-linear Canonical Correlation Analysis: A Compressed Representation Approachcs.LG

Canonical Correlation Analysis (CCA) is a linear representation learning method that seeks maximally correlated variables in multi-view data. Non-linear CCA extends this notion to a broader family of transformations, which are more powerful in many real-world applications. Given the joint probability, the Alternating C…

2018-10-31abs ↗pdf ↗

Efficient AUC Optimization for Information Ranking Applicationscs.IR

Adequate evaluation of an information retrieval system to estimate future performance is a crucial task. Area under the ROC curve (AUC) is widely used to evaluate the generalization of a retrieval system. However, the objective function optimized in many retrieval systems is the error rate and not the AUC value. This p…

2015-11-16abs ↗pdf ↗

Probabilistic inverse optimal control for non-linear partially observable systems disentangles perceptual uncertainty and behavioral costscs.LG

New method disentangles perceptual uncertainty and behavioral costs in partially observable systems.

problem Tackles inverse optimal control for non-linear partially observable systems.

method Probabilistic approach using maximum causal entropy formulations and local linearization.

result Disentangles perceptual factors and behavioral costs in sequential decision-making.

inverse optimal control non-linear systems partially observable perceptual uncertainty behavioral costs

2023-03-29abs ↗pdf ↗

Nonlinear Inductive Matrix Completion based on One-layer Neural Networkscs.LG

The goal of a recommendation system is to predict the interest of a user in a given item by exploiting the existing set of ratings as well as certain user/item features. A standard approach to modeling this problem is Inductive Matrix Completion where the predicted rating is modeled as an inner product of the user and …

2018-05-26abs ↗pdf ↗

Generalized Linear Bandits: Almost Optimal Regret with One-Pass Updatecs.LG

New algorithm achieves nearly optimal regret with one-pass updates for GLB problems.

problem Generalized linear bandits with non-linear reward distributions.

method Jointly efficient algorithm using OMD estimator with one-pass updates.

result Nearly optimal regret bound with

\mathcal{O}(1)

time and space complexities per round.

Generalized Linear Bandits Optimistic Methods One-Pass Updates Regret Minimization Non-Linear Reward

2025-07-16abs ↗pdf ↗

Simultaneous off-the-grid learning of mixtures issued from a continuous dictionarystat.ML

Estimates signals from a continuous dictionary with sparse mixtures using optimization.

problem Estimating signals from a continuous dictionary with unknown mixtures and noise.

method Formulates a regularized optimization problem with data fidelity and

(\ell_1,L^p)

-penalty.

result High probability bounds on prediction error for the Group-Nonlinear-Lasso solution.

signal estimation continuous dictionary sparse mixtures non-linear parameters optimization

2022-10-27abs ↗pdf ↗