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

count % of corpus

48 results for “functional learning”

Learning the gravitational force law and other analytic functionscs.LG

Wide neural networks can learn complex functions like gravitational force law.

problem Learning complex functions like gravitational force law with neural networks.

method Extending theoretical bounds to analytic functions on the sphere using SGD and ReLU networks.

result Wide ReLU networks can learn analytic functions efficiently with proportional number of samples.

neural networks learning bounds analytic functions gravitational force ReLU networks

2020-05-15abs ↗pdf ↗

Representation Learning on Graphs: A Reinforcement Learning Applicationcs.LG

In this work, we study value function approximation in reinforcement learning (RL) problems with high dimensional state or action spaces via a generalized version of representation policy iteration (RPI). We consider the limitations of proto-value functions (PVFs) at accurately approximating the value function in low d…

2019-01-16abs ↗pdf ↗

Functional Bilevel Optimization for Machine Learningstat.ML

New approach to bilevel optimization for machine learning using functional methods.

problem Solving bilevel optimization problems in machine learning, especially with over-parameterized neural networks.

method Functional point of view, scalable and efficient algorithms for functional bilevel optimization.

result Demonstrates benefits of functional approach on instrumental regression and reinforcement learning tasks.

bilevel optimization machine learning functional methods reinforcement learning over-parameterized networks

2024-03-29abs ↗pdf ↗

Meta-Learning Mean Functions for Gaussian Processesstat.ML

When fitting Bayesian machine learning models on scarce data, the main challenge is to obtain suitable prior knowledge and encode it into the model. Recent advances in meta-learning offer powerful methods for extracting such prior knowledge from data acquired in related tasks. When it comes to meta-learning in Gaussian…

2019-01-23abs ↗pdf ↗

Curriculum Learning with a Progression Functioncs.LG

Paper introduces a new curriculum generation method for reinforcement learning.

problem Improving reinforcement learning performance and speed through curriculum learning.

method The paper proposes a novel curriculum generation paradigm based on progression and mapping functions.

result Empirical results show the new approach outperforms state-of-the-art algorithms.

Curriculum Learning Reinforcement Learning Progression Function Mapping Function Performance Improvement

2020-08-02abs ↗pdf ↗

Function-Space Learning Ratesstat.ML

Develops methods to measure and set function-space learning rates in neural networks.

problem Measuring and optimizing changes in neural network output functions.

method Efficient methods to measure and set function-space learning rates, requiring minimal computational overhead.

result Demonstrates FLeRM (Function-space Learning Rate Matching) for hyperparameter transfer across model scales.

neural networks learning rates function space hyperparameter transfer optimization

2025-02-24abs ↗pdf ↗

The Probably Approximately Correct Learning Model in Computational Learning Theorystat.ML

Survey on learning Boolean functions in computational theory.

problem Learning Boolean function classes in computational theory.

method Overview of known results in PAC and related models.

result Discussion of various learning results for Boolean functions.

PAC learning Boolean functions computational theory learning theory

2025-11-11abs ↗pdf ↗

Distributed Gradient Descent for Functional Learningstat.ML

A new algorithm for learning from functional data across multiple machines.

problem Handling large-scale functional data analysis.

method Distributed Gradient Descent Functional Learning (DGDFL) algorithm.

result First theoretical understanding and optimal learning rates for DGDFL.

functional data analysis distributed learning gradient descent reproducing kernel Hilbert space semi-supervised learning

2023-05-12abs ↗pdf ↗

Supervised Manifold Learning for Functional Datastat.ME

A new method for functional data classification using supervised manifold learning.

problem Improving classification of functional data.

method Supervised manifold learning approach considering label information.

result The proposed method achieves highly competitive performance compared to existing methods.

functional data manifold learning classification supervised learning proximity measure

2025-03-23abs ↗pdf ↗

Geodesic Distance Function Learning via Heat Flow on Vector Fieldscs.LG

Learning a distance function or metric on a given data manifold is of great importance in machine learning and pattern recognition. Many of the previous works first embed the manifold to Euclidean space and then learn the distance function. However, such a scheme might not faithfully preserve the distance function if t…

2014-05-01abs ↗pdf ↗

Offline Reinforcement Learning with Differentiable Function Approximation is Provably Efficientcs.LG

Efficient offline reinforcement learning with neural networks using differentiable function approximation.

problem Statistical efficiency of offline reinforcement learning with function approximators.

method Pessimistic fitted Q-learning (PFQL) and differentiable function approximation.

result Provably efficient offline reinforcement learning with differentiable function approximation.

reinforcement learning offline learning differentiable function approximation Pessimistic fitted Q-learning statistical efficiency

2022-10-03abs ↗pdf ↗

Continuous-time reinforcement learning: ellipticity enables model-free value function approximationcs.LG

New algorithm learns value and advantage functions for continuous-time Markov processes without structural assumptions.

problem Learning value and advantage functions for continuous-time Markov processes without structural assumptions.

method Proposes Sobolev-prox fitted

q

-learning algorithm based on Hilbert-space positive definiteness and boundedness properties of Bellman operators.

result Identifies ellipticity as a key structural property enabling reinforcement learning for Markov diffusions.

reinforcement learning continuous-time Markov processes ellipticity function approximation Hilbert-space

2026-02-06abs ↗pdf ↗

Operator-valued Kernels for Learning from Functional Response Datacs.LG

In this paper we consider the problems of supervised classification and regression in the case where attributes and labels are functions: a data is represented by a set of functions, and the label is also a function. We focus on the use of reproducing kernel Hilbert space theory to learn from such functional data. Basi…

2015-10-28abs ↗pdf ↗

Regression with Linear Factored Functionscs.LG

Many applications that use empirically estimated functions face a curse of dimensionality, because the integrals over most function classes must be approximated by sampling. This paper introduces a novel regression-algorithm that learns linear factored functions (LFF). This class of functions has structural properties …

2014-12-19abs ↗pdf ↗

q-Learning in Continuous Timecs.LG

Continuous-time Q-learning theory developed for reinforcement learning.

problem Continuous-time reinforcement learning challenges.

method Entropy-regularized, exploratory diffusion process formulation; first-order approximation of Q-function; martingale conditions.

result Developed a q-learning theory independent of time discretization.

reinforcement learning continuous time Q-learning entropy regularization martingales

2022-07-02abs ↗pdf ↗

Functional Autoencoder for Smoothing and Representation Learningcs.LG

Proposes a neural network autoencoder for smoothing and representation learning of functional data.

problem Lack of sufficient nonlinear representations in existing methods for functional data analysis.

method Develops a neural network autoencoder architecture to process functional data directly, learning both smoothing and representation.

result Outperforms traditional methods in prediction, classification, and computational efficiency.

functional data analysis autoencoder smoothing representation learning neural networks

2024-01-17abs ↗pdf ↗

Provably Efficient

Q

-learning with Function Approximation via Distribution Shift Error Checking Oraclecs.LG

$Q$ -learning with function approximation is one of the most popular methods in reinforcement learning. Though the idea of using function approximation was proposed at least 60 years ago, even in the simplest setup, i.e, approximating $Q$ -functions with linear functions, it is still an open problem on how to design a pr…

2019-06-14abs ↗pdf ↗

Deep Learning for Functional Data Analysis with Adaptive Basis Layersstat.ML

Adaptive neural networks learn functional data bases for improved performance.

problem Applying deep learning to functional data is challenging due to high dimensionality.

method Proposes adaptive neural networks with Basis Layers that learn relevant basis functions.

result Empirically outperforms other neural network approaches across various tasks.

deep learning functional data basis learning neural networks end-to-end

2021-06-19abs ↗pdf ↗

Off-Policy Adversarial Inverse Reinforcement Learningcs.LG

Improves imitation learning in RL by learning reward function efficiently.

problem Lack of effective reward function approximation in AIRL for imitation tasks.

method Proposes Off-Policy AIRL that combines adversarial learning with efficient reward function approximation.

result Shows superior imitation performance and efficiency compared to state-of-the-art AIL algorithms.

Reinforcement Learning Adversarial Learning Reward Function Inverse Reinforcement Learning Efficiency

2020-05-03abs ↗pdf ↗

Collective Loss Function for Positive and Unlabeled Learningcs.LG

Paper proposes a new loss function for PU learning without negative examples.

problem Traditional machine learning struggles with negative examples, leading to biased predictions.

method Developed a collective loss function (cPU) for positive and unlabeled data.

result The cPU consistently outperforms existing methods in PU learning benchmarks and real-world datasets.

PU learning positive and unlabeled collective loss function machine learning

2020-05-06abs ↗pdf ↗

m-arcsinh: An Efficient and Reliable Function for SVM and MLP in scikit-learncs.LG

m-arcsinh improves SVM and MLP reliability and speed in scikit-learn.

problem Improving SVM and MLP reliability and speed in scikit-learn.

method Modified arcsinh function for kernel and activation in SVM and MLP.

result Competitive classification performance and reliability of SVM and MLP with m-arcsinh.

m-arcsinh SVM MLP scikit-learn kernel

2020-09-16abs ↗pdf ↗

Discovering Parametric Activation Functionscs.LG

Automatically discovers effective activation functions for deep learning.

problem Inconsistent performance of novel activation functions in deep learning networks.

method Evolutionary search for general form, gradient descent for parameters.

result Significant performance improvements over ReLU and other functions.

activation functions deep learning neural networks performance optimization evolutionary search

2020-06-05abs ↗pdf ↗

Deep Radial-Basis Value Functions for Continuous Controlcs.LG

A core operation in reinforcement learning (RL) is finding an action that is optimal with respect to a learned value function. This operation is often challenging when the learned value function takes continuous actions as input. We introduce deep radial-basis value functions (RBVFs): value functions learned using a de…

2020-02-05abs ↗pdf ↗

A Resolution Independent Neural Operatorcs.LG

RI-DeepONet learns neural operators from arbitrary sensor data.

problem Discretization of input functions limits practical applications of DeepONet.

method Introduces RI-DeepONet and two dictionary learning algorithms for INRs.

result RINO handles arbitrary sensor data robustly and applies to various problems.

DeepONet resolution independence neural operator dictionary learning INR

2024-07-17abs ↗pdf ↗

Hierarchical Universal Value Function Approximatorscs.LG

Develops hierarchical reinforcement learning value function approximators.

problem Estimating long-term returns in reinforcement learning with multiple goals.

method Introduces hierarchical universal value function approximators (H-UVFAs) using the options framework.

result Demonstrates generalization and improved performance of H-UVFAs over UVFAs.

reinforcement learning universal approximators hierarchical value functions temporal abstraction options framework

2024-10-11abs ↗pdf ↗

Accelerated Distributional Temporal Difference Learning with Linear Function Approximationstat.ML

New algorithms improve distributional TD learning with linear approximations.

problem Estimating return distributions in reinforcement learning.

method Fine-grained analysis of linear-categorical Bellman equation, variance reduction techniques.

result Tight sample complexity bounds for distributional TD learning with linear approximations.

reinforcement learning temporal difference learning distributional reinforcement linear function approximation variance reduction

2025-11-16abs ↗pdf ↗

A Functional Perspective on Learning Symmetric Functions with Neural Networkscs.LG

New neural network models learn symmetric functions of varying input sizes.

problem Learning symmetric functions with varying input sizes.

method Functional perspective on neural networks, treating symmetric functions as functions over probability measures.

result Established approximation and generalization bounds for shallow architectures that extend across input sizes.

Neural Networks Symmetric Functions Probability Measures Functional Spaces Generalization Guarantees

2020-08-16abs ↗pdf ↗

Statistical Depth Meets Machine Learning: Kernel Mean Embeddings and Depth in Functional Data Analysismath.ST

This paper connects functional data analysis with machine learning techniques.

problem Lack of theoretical analysis for functional depths.

method Viewing functional depths as kernel mean embeddings in machine learning.

result Facilitates answers to open questions about functional depths.

functional data analysis kernel mean embedding statistical depth machine learning

2021-05-26abs ↗pdf ↗

Estimating Structural Target Functions using Machine Learning and Influence Functionsstat.ME

New framework estimates target functions from incomplete data.

problem Estimating target functions from partially observed data.

method IF-learning framework using influence functions.

result Two learning algorithms developed for estimation.

machine learning influence functions target functions statistical learning coarsening at random

2020-08-14abs ↗pdf ↗

Activation Functions for Generalized Learning Vector Quantization - A Performance Comparisoncs.LG

An appropriate choice of the activation function (like ReLU, sigmoid or swish) plays an important role in the performance of (deep) multilayer perceptrons (MLP) for classification and regression learning. Prototype-based classification learning methods like (generalized) learning vector quantization (GLVQ) are powerful…

2019-01-17abs ↗pdf ↗

Learning Set Functions that are Sparse in Non-Orthogonal Fourier Basescs.LG

New algorithms learn sparse set functions in non-orthogonal Fourier bases.

problem Learning sparse set functions in non-orthogonal Fourier bases.

method Novel algorithms using non-orthogonal Fourier transforms.

result At most

nk - k \log_2 k + k

queries for

k

non-zero Fourier coefficients.

set functions Fourier sparsity non-orthogonal transforms sparse learning machine learning

2020-10-01abs ↗pdf ↗

Growing axons: greedy learning of neural networks with application to function approximationcs.LG

We propose a new method for learning deep neural network models that is based on a greedy learning approach: we add one basis function at a time, and a new basis function is generated as a non-linear activation function applied to a linear combination of the previous basis functions. Such a method (growing deep neural …

2019-10-28abs ↗pdf ↗

Learning to be Global Optimizercs.LG

This paper proposes a new global optimization algorithm using deep learning.

problem Developing efficient algorithms for global optimization of non-convex functions.

method Two-phase approach: minimization phase with model-driven deep learning, escaping phase with reinforcement learning.

result The proposed algorithm significantly outperforms classical optimization methods and handles ill-posed functions.

global optimization deep learning reinforcement learning non-convex functions Markov decision process

2020-03-10abs ↗pdf ↗

Inverse Mixed-Integer Programming: Learning Constraints then Objective Functionsmath.OC

Proposes a method to learn both constraints and objective functions from data.

problem Data-driven inverse optimization for mixed-integer linear programs (MILPs).

method Two-stage approach: first learns constraints, then estimates objective-function weights conditioned on learned constraints.

result Proposes and validates a method for learning both objective functions and constraints from data.

inverse optimization mixed-integer programming learning constraints learning objectives pseudo-metric spaces

2025-10-06abs ↗pdf ↗

Local transfer learning from one data space to anothercs.LG

The paper explores transferring functions from one data space to another.

problem Approximating a function on a new data set using a learned function from an old data set.

method Transfer learning from one data space to another, focusing on subsets of the target data space.

result Local smoothness of the function and its lifting are related.

transfer learning data space inverse problems function approximation meta-learning

2023-02-01abs ↗pdf ↗

Beyond Exponentially Discounted Sum: Automatic Learning of Return Functioncs.LG

In reinforcement learning, Return, which is the weighted accumulated future rewards, and Value, which is the expected return, serve as the objective that guides the learning of the policy. In classic RL, return is defined as the exponentially discounted sum of future rewards. One key insight is that there could be many…

2019-05-28abs ↗pdf ↗

A Theory of Nonparametric Covariance Function Estimation for Discretely Observed Datamath.ST

Study nonparametric covariance function estimation for noisy data.

problem Estimating covariance function from discrete noisy data in high dimensions.

method Adaptive learning-based estimators, including deep learning.

result Established oracle inequality and convergence rates for deep learning estimators.

covariance function nonparametric estimation discrete data deep learning oracle inequality

2026-03-24abs ↗pdf ↗

Incrementally Learning Functions of the Returncs.LG

Temporal difference methods enable efficient estimation of value functions in reinforcement learning in an incremental fashion, and are of broader interest because they correspond learning as observed in biological systems. Standard value functions correspond to the expected value of a sum of discounted returns. While …

2019-07-05abs ↗pdf ↗

Boosting Soft Q-Learning by Boundingcs.LG

Boosts Q-learning by using value function bounds.

problem Efficiently solving new tasks using past experience.

method Derives double-sided bounds on optimal value function and uses them to update Q-function.

result Boosted training performance through alternative Q-function update method.

Q-learning value function bounds performance boost

2024-06-26abs ↗pdf ↗

Neural Feature Learning in Function Spacecs.LG

A new framework learns system design using neural features in function space.

problem Learning system design with neural feature extractors.

method Introduces feature geometry in function space, nesting technique for optimal feature approximation.

result Optimal features found from data samples using off-the-shelf architectures and optimizers.

Neural Feature Learning Function Space Statistical Dependence Optimal Features Off-the-Shelf Architectures

2023-09-18abs ↗pdf ↗

Interplay between depth of neural networks and locality of target functionscs.LG

Deep neural networks perform well on local tasks but struggle with global tasks.

problem Understanding the limitations of overparameterized deep neural networks in learning global functions.

method Introduced

k

-local and

k

-global functions to study the interplay between depth and function locality.

result Depth is beneficial for learning local functions but detrimental to learning global functions.

deep learning neural networks generalization locality global function

2022-01-28abs ↗pdf ↗

A Finite Sample Analysis of Distributional TD Learning with Linear Function Approximationstat.ML

Study on distributional TD learning with linear approximations for better return estimation.

problem Estimating the return distribution of a policy in reinforcement learning.

method Finite-sample analysis of distributional TD learning with linear function approximation, using the linear-categorical Bellman equation and exponential stability arguments for products of random matrices.

result Sample complexity of linear distributional TD learning matches that of classic linear TD learning, indicating similar difficulty in estimating return distribution versus its expectation.

distributional reinforcement learning temporal difference learning linear function approximation return distribution Markov decision process

2025-02-20abs ↗pdf ↗

KKANs: Kurkova-Kolmogorov-Arnold Networks and Their Learning Dynamicscs.LG

Proposes a new neural network architecture combining MLP and basis functions.

problem Function approximation and operator learning in scientific machine learning.

method Combines robust MLP inner functions with flexible basis functions outer functions.

result KKAN outperforms MLPs and KANs in function approximation and operator learning tasks.

Kurkova-Kolmogorov-Arnold Networks Universal Approximator Function Regression Physics-Informed Machine Learning Operator Learning

2024-12-21abs ↗pdf ↗

Learning low-degree functions from a logarithmic number of random queriescs.LG

Learn low-degree functions with few random queries.

problem Learning low-degree functions from limited random queries.

method Learn bounded functions

f:\{-1,1\}^n o[-1,1]

of degree at most

d

with

L_2

-accuracy

\varepsilon

and confidence

1-δ

from

\log( frac{n}δ)\,\varepsilon^{-d-1} C^{d^{3/2}\sqrt{\log d}}

random queries.

result Learn low-degree functions efficiently with logarithmic number of random queries.

machine learning low-degree functions random queries accuracy confidence

2021-09-21abs ↗pdf ↗

Risk Bounds for Robust Deep Learningcs.LG

The paper proves deep learning can be robust with certain loss functions.

problem The robustness of deep learning models under flawed data.

method Empirical-risk minimization with unbounded, Lipschitz-continuous loss functions.

result These loss functions provide efficient prediction under minimal data assumptions.

deep learning robustness loss functions empirical-risk minimization Lipschitz continuity

2020-09-14abs ↗pdf ↗

Ratio-based Loss Functionsstat.ML

This paper explores ratio-based loss functions for machine learning.

problem Margin-based and distance-based loss functions for classification and regression.

method Investigation of ratio-based loss functions' properties.

result Proposed new ratio-based loss functions for regression.

machine learning loss functions ratio-based regression classification

2026-05-07abs ↗pdf ↗

A Doubly Robust Machine Learning Approach for Disentangling Treatment Effect Heterogeneity with Functional Outcomesstat.ME

FOCaL meta-learner estimates functional treatment effects robustly.

problem Estimating heterogeneous treatment effects from functional outcomes.

method Doubly robust meta-learner FOCaL integrating functional regression.

result Direct and robust estimation of F-CATE.

FOCaL Functional Outcome Causal Learning Doubly Robust Heterogeneous Treatment Effects Functional Regression

2026-02-11abs ↗pdf ↗

Online Regularized Learning Algorithm for Functional Datastat.ML

Paper develops an online learning algorithm for functional data models.

problem Recovering slope functions or predictors in functional data models.

method Online regularized learning algorithm in reproducing kernel Hilbert spaces with polynomially decaying step-size.

result Established fast convergence rates for estimation error without capacity assumption.

functional data reproducing kernel Hilbert spaces online learning regularization excess prediction error

2022-11-24abs ↗pdf ↗