Anastasis Kratsios

Ruiyang Hong

Jose Antonio Lara Benitez

Neural Networks, 2024

Out-of-distributional risk bounds for neural operators with applications to the Helmholtz equation.

[BibT_eX]

[DOI]

J. Comput. Phys., 2024

Neural Operators Can Play Dynamic Stackelberg Games.

[BibT_eX]

[DOI]

CoRR, 2024

Scalable Message Passing Neural Networks: No Need for Attention in Large Graph Representation Learning.

[BibT_eX]

[DOI]

CoRR, 2024

A Comprehensive Analysis on the Learning Curve in Kernel Ridge Regression.

[BibT_eX]

[DOI]

CoRR, 2024

Simultaneously Solving FBSDEs with Neural Operators of Logarithmic Depth, Constant Width, and Sub-Linear Rank.

[BibT_eX]

[DOI]

Takashi Furuya

CoRR, 2024

Inverse Entropic Optimal Transport Solves Semi-supervised Learning via Data Likelihood Maximization.

[BibT_eX]

[DOI]

CoRR, 2024

Bridging the Gap Between Approximation and Learning via Optimal Approximation by ReLU MLPs of Maximal Regularity.

[BibT_eX]

[DOI]

Ruiyang Hong

CoRR, 2024

Neural Spacetimes for DAG Representation Learning.

[BibT_eX]

[DOI]

CoRR, 2024

Filtered not Mixed: Stochastic Filtering-Based Online Gating for Mixture of Large Language Models.

[BibT_eX]

[DOI]

CoRR, 2024

Low-dimensional approximations of the conditional law of Volterra processes: a non-positive curvature approach.

[BibT_eX]

[DOI]

CoRR, 2024

Reality Only Happens Once: Single-Path Generalization Bounds for Transformers.

[BibT_eX]

[DOI]

CoRR, 2024

Mixture of Experts Soften the Curse of Dimensionality in Operator Learning.

[BibT_eX]

[DOI]

Jose Antonio Lara Benitez

Takashi Furuya

Matti Lassas

Maarten V. de Hoop

CoRR, 2024

Digital Computers Break the Curse of Dimensionality: Adaptive Bounds via Finite Geometry.

[BibT_eX]

[DOI]

A. Martina Neuman

Gudmund Pammer

CoRR, 2024

Breaking the Curse of Dimensionality with Distributed Neural Computation.

[BibT_eX]

[DOI]

Takashi Furuya

Marc T. Law

CoRR, 2024

Characterizing Overfitting in Kernel Ridgeless Regression Through the Eigenspectrum.

[BibT_eX]

[DOI]

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Neural Snowflakes: Universal Latent Graph Inference via Trainable Latent Geometries.

[BibT_eX]

[DOI]

Proceedings of the Twelfth International Conference on Learning Representations, 2024

2023

Denise: Deep Robust Principal Component Analysis for Positive Semidefinite Matrices.

[BibT_eX]

[DOI]

Trans. Mach. Learn. Res., 2023

Small Transformers Compute Universal Metric Embeddings.

[BibT_eX]

[DOI]

Valentin Debarnot

Ivan Dokmanic

J. Mach. Learn. Res., 2023

Instance-Dependent Generalization Bounds via Optimal Transport.

[BibT_eX]

[DOI]

J. Mach. Learn. Res., 2023

Deep Kalman Filters Can Filter.

[BibT_eX]

[DOI]

CoRR, 2023

Regret-Optimal Federated Transfer Learning for Kernel Regression with Applications in American Option Pricing.

[BibT_eX]

[DOI]

CoRR, 2023

A Transfer Principle: Universal Approximators Between Metric Spaces From Euclidean Universal Approximators.

[BibT_eX]

[DOI]

CoRR, 2023

Generative Ornstein-Uhlenbeck Markets via Geometric Deep Learning.

[BibT_eX]

[DOI]

CoRR, 2023

A Theoretical Analysis of the Test Error of Finite-Rank Kernel Ridge Regression.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

2022

Do ReLU Networks Have An Edge When Approximating Compactly-Supported Functions?

[BibT_eX]

[DOI]

Trans. Mach. Learn. Res., 2022

Universal Approximation Theorems for Differentiable Geometric Deep Learning.

[BibT_eX]

[DOI]

Leonie Papon

J. Mach. Learn. Res., 2022

Learning sub-patterns in piecewise continuous functions.

[BibT_eX]

[DOI]

Neurocomputing, 2022

Designing Universal Causal Deep Learning Models: The Case of Infinite-Dimensional Dynamical Systems from Stochastic Analysis.

[BibT_eX]

[DOI]

Luca Galimberti

Giulia Livieri

CoRR, 2022

Piecewise-Linear Activations or Analytic Activation Functions: Which Produce More Expressive Neural Networks?

[BibT_eX]

[DOI]

CoRR, 2022

Metric Hypertransformers are Universal Adapted Maps.

[BibT_eX]

[DOI]

Beatrice Acciaio

Gudmund Pammer

CoRR, 2022

Universal Approximation Under Constraints is Possible with Transformers.

[BibT_eX]

[DOI]

Proceedings of the Tenth International Conference on Learning Representations, 2022

2021

NEU: A Meta-Algorithm for Universal UAP-Invariant Feature Representation.

[BibT_eX]

[DOI]

J. Mach. Learn. Res., 2021

Universal Regular Conditional Distributions via Probability Measure-Valued Deep Neural Models.

[BibT_eX]

[DOI]

CoRR, 2021

Quantitative Rates and Fundamental Obstructions to Non-Euclidean Universal Approximation with Deep Narrow Feed-Forward Networks.

[BibT_eX]

[DOI]

Leonie Papon

CoRR, 2021

The Universal Approximation Property.

[BibT_eX]

[DOI]

Ann. Math. Artif. Intell., 2021

Generative OrnsteinUhlenbeck Markets via Geometric Deep Learning.

[BibT_eX]

[DOI]

Proceedings of the Geometric Science of Information - 6th International Conference, 2021

Optimizing Optimizers: Regret-optimal gradient descent algorithms.

[BibT_eX]

[DOI]

Philippe Casgrain

Proceedings of the Conference on Learning Theory, 2021

2020

Overcoming The Limitations of Neural Networks in Composite-Pattern Learning with Architopes.

[BibT_eX]

[DOI]

CoRR, 2020

Architopes: An Architecture Modification for Composite Pattern Learning, Increased Expressiveness, and Reduced Training Time.

[BibT_eX]

[DOI]

CoRR, 2020

Non-Euclidean Universal Approximation.

[BibT_eX]

[DOI]

Ievgen Bilokopytov

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

2019

Universal Approximation Theorems.

[BibT_eX]

[DOI]

CoRR, 2019

2018

The NEU Meta-Algorithm for Geometric Learning with Applications in Finance.

[BibT_eX]

[DOI]