Anastasis Kratsios

According to our database, Anastasis Kratsios authored at least 33 papers between 2018 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2024

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

Reza Arabpour, John Armstrong, Luca Galimberti, Anastasis Kratsios, Giulia Livieri

CoRR, 2024

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

Yannick Limmer, Anastasis Kratsios, Xuwei Yang, Raeid Saqur, Blanka Horvath

CoRR, 2024

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

Anastasis Kratsios, Takashi Furuya, Jose Antonio Lara Benitez, Matti Lassas, Maarten V. de Hoop

CoRR, 2024

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

Anastasis Kratsios, A. Martina Neuman, Gudmund Pammer

CoRR, 2024

Breaking the Curse of Dimensionality with Distributed Neural Computation.

Haitz Sáez de Ocáriz Borde, Takashi Furuya, Anastasis Kratsios, Marc T. Law

CoRR, 2024

Characterizing Overfitting in Kernel Ridgeless Regression Through the Eigenspectrum.

Tin Sum Cheng, Aurélien Lucchi, Anastasis Kratsios, David Belius

CoRR, 2024

2023

Small Transformers Compute Universal Metric Embeddings.

Anastasis Kratsios, Valentin Debarnot, Ivan Dokmanic

J. Mach. Learn. Res., 2023

Deep Kalman Filters Can Filter.

Blanka Hovart, Anastasis Kratsios, Yannick Limmer, Xuwei Yang

CoRR, 2023

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

Haitz Sáez de Ocáriz Borde, Anastasis Kratsios

CoRR, 2023

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

Xuwei Yang, Anastasis Kratsios, Florian Krach, Matheus R. Grasselli, Aurélien Lucchi

CoRR, 2023

Capacity Bounds for Hyperbolic Neural Network Representations of Latent Tree Structures.

Anastasis Kratsios, Ruiyang Hong, Haitz Sáez de Ocáriz Borde

CoRR, 2023

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

Anastasis Kratsios, Chong Liu, Matti Lassas, Maarten V. de Hoop, Ivan Dokmanic

CoRR, 2023

Generative Ornstein-Uhlenbeck Markets via Geometric Deep Learning.

Anastasis Kratsios, Cody B. Hyndman

CoRR, 2023

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

Tin Sum Cheng, Aurélien Lucchi, Anastasis Kratsios, Ivan Dokmanic, David Belius

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?

Anastasis Kratsios, Behnoosh Zamanlooy

Trans. Mach. Learn. Res., 2022

Universal Approximation Theorems for Differentiable Geometric Deep Learning.

Anastasis Kratsios, Leonie Papon

J. Mach. Learn. Res., 2022

Learning sub-patterns in piecewise continuous functions.

Anastasis Kratsios, Behnoosh Zamanlooy

Neurocomputing, 2022

Instance-Dependent Generalization Bounds via Optimal Transport.

Songyan Hou, Parnian Kassraie, Anastasis Kratsios, Jonas Rothfuss, Andreas Krause

CoRR, 2022

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

Luca Galimberti, Giulia Livieri, Anastasis Kratsios

CoRR, 2022

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

Anastasis Kratsios, Behnoosh Zamanlooy

CoRR, 2022

Metric Hypertransformers are Universal Adapted Maps.

Beatrice Acciaio, Anastasis Kratsios, Gudmund Pammer

CoRR, 2022

Universal Approximation Under Constraints is Possible with Transformers.

Anastasis Kratsios, Behnoosh Zamanlooy, Tianlin Liu, Ivan Dokmanic

Proceedings of the Tenth International Conference on Learning Representations, 2022

2021

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

Anastasis Kratsios, Cody B. Hyndman

J. Mach. Learn. Res., 2021

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

Anastasis Kratsios

CoRR, 2021

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

Anastasis Kratsios, Leonie Papon

CoRR, 2021

The Universal Approximation Property.

Anastasis Kratsios

Ann. Math. Artif. Intell., 2021

Generative OrnsteinUhlenbeck Markets via Geometric Deep Learning.

Anastasis Kratsios, Cody B. Hyndman

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

Optimizing Optimizers: Regret-optimal gradient descent algorithms.

Philippe Casgrain, Anastasis Kratsios

Proceedings of the Conference on Learning Theory, 2021

2020

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

Anastasis Kratsios, Behnoosh Zamanlooy

CoRR, 2020

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

Anastasis Kratsios, Behnoosh Zamanlooy

CoRR, 2020

Non-Euclidean Universal Approximation.

Anastasis Kratsios, 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.

Anastasis Kratsios

CoRR, 2019

2018

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

Anastasis Kratsios, Cody B. Hyndman

CoRR, 2018