default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDAnastasis Kratsios
Person information
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
2020 – today
- 2024
[j10]Jose Antonio Lara Benitez
, Takashi Furuya, Florian Faucher, Anastasis Kratsios, Xavier Tricoche, Maarten V. de Hoop:
Out-of-distributional risk bounds for neural operators with applications to the Helmholtz equation. J. Comput. Phys. 513: 113168 (2024)- [j9]Anastasis Kratsios, Ruiyang Hong, Haitz Sáez de Ocáriz Borde:
Capacity bounds for hyperbolic neural network representations of latent tree structures. Neural Networks 178: 106420 (2024) - [c7]Haitz Sáez de Ocáriz Borde, Anastasis Kratsios:
Neural Snowflakes: Universal Latent Graph Inference via Trainable Latent Geometries. ICLR 2024 - [c6]Tin Sum Cheng, Aurélien Lucchi, Anastasis Kratsios, David Belius:
Characterizing Overfitting in Kernel Ridgeless Regression Through the Eigenspectrum. ICML 2024 - [i35]Tin Sum Cheng, Aurélien Lucchi, Anastasis Kratsios, David Belius:
Characterizing Overfitting in Kernel Ridgeless Regression Through the Eigenspectrum. CoRR abs/2402.01297 (2024) - [i34]Haitz Sáez de Ocáriz Borde, Takashi Furuya, Anastasis Kratsios, Marc T. Law:
Breaking the Curse of Dimensionality with Distributed Neural Computation. CoRR abs/2402.03460 (2024) - [i33]Anastasis Kratsios, A. Martina Neuman, Gudmund Pammer:
Digital Computers Break the Curse of Dimensionality: Adaptive Bounds via Finite Geometry. CoRR abs/2402.05576 (2024) - [i32]Anastasis Kratsios, Takashi Furuya, Jose Antonio Lara Benitez, Matti Lassas, Maarten V. de Hoop:
Mixture of Experts Soften the Curse of Dimensionality in Operator Learning. CoRR abs/2404.09101 (2024) - [i31]Yannick Limmer, Anastasis Kratsios, Xuwei Yang, Raeid Saqur, Blanka Horvath:
Reality Only Happens Once: Single-Path Generalization Bounds for Transformers. CoRR abs/2405.16563 (2024) - [i30]Reza Arabpour, John Armstrong, Luca Galimberti, Anastasis Kratsios, Giulia Livieri:
Low-dimensional approximations of the conditional law of Volterra processes: a non-positive curvature approach. CoRR abs/2405.20094 (2024) - [i29]Raeid Saqur, Anastasis Kratsios, Florian Krach, Yannick Limmer, Jacob-Junqi Tian, John Willes, Blanka Horvath, Frank Rudzicz:
Filtered not Mixed: Stochastic Filtering-Based Online Gating for Mixture of Large Language Models. CoRR abs/2406.02969 (2024) - [i28]Haitz Sáez de Ocáriz Borde, Anastasis Kratsios, Marc T. Law, Xiaowen Dong, Michael M. Bronstein:
Neural Spacetimes for DAG Representation Learning. CoRR abs/2408.13885 (2024) - [i27]Ruiyang Hong, Anastasis Kratsios:
Bridging the Gap Between Approximation and Learning via Optimal Approximation by ReLU MLPs of Maximal Regularity. CoRR abs/2409.12335 (2024) - [i26]Mikhail Persiianov, Arip Asadulaev, Nikita Andreev, Nikita Starodubcev, Dmitry Baranchuk, Anastasis Kratsios, Evgeny Burnaev, Alexander Korotin:
Inverse Entropic Optimal Transport Solves Semi-supervised Learning via Data Likelihood Maximization. CoRR abs/2410.02628 (2024) - [i25]Takashi Furuya, Anastasis Kratsios:
Simultaneously Solving FBSDEs with Neural Operators of Logarithmic Depth, Constant Width, and Sub-Linear Rank. CoRR abs/2410.14788 (2024) - [i24]Tin Sum Cheng, Aurélien Lucchi, Anastasis Kratsios, David Belius:
A Comprehensive Analysis on the Learning Curve in Kernel Ridge Regression. CoRR abs/2410.17796 (2024) - [i23]Haitz Sáez de Ocáriz Borde, Artem Lukoianov, Anastasis Kratsios, Michael M. Bronstein, Xiaowen Dong:
Scalable Message Passing Neural Networks: No Need for Attention in Large Graph Representation Learning. CoRR abs/2411.00835 (2024) - [i22]Guillermo Alvarez, Ibrahim Ekren, Anastasis Kratsios, Xuwei Yang:
Neural Operators Can Play Dynamic Stackelberg Games. CoRR abs/2411.09644 (2024) - 2023
- [j8]Anastasis Kratsios, Valentin Debarnot, Ivan Dokmanic:
Small Transformers Compute Universal Metric Embeddings. J. Mach. Learn. Res. 24: 170:1-170:48 (2023) - [j7]Songyan Hou, Parnian Kassraie, Anastasis Kratsios, Andreas Krause, Jonas Rothfuss:
Instance-Dependent Generalization Bounds via Optimal Transport. J. Mach. Learn. Res. 24: 349:1-349:51 (2023) - [j6]Calypso Herrera, Florian Krach, Anastasis Kratsios, Pierre Ruyssen, Josef Teichmann:
Denise: Deep Robust Principal Component Analysis for Positive Semidefinite Matrices. Trans. Mach. Learn. Res. 2023 (2023) - [c5]Tin Sum Cheng, Aurélien Lucchi, Anastasis Kratsios, Ivan Dokmanic, David Belius:
A Theoretical Analysis of the Test Error of Finite-Rank Kernel Ridge Regression. NeurIPS 2023 - [i21]Anastasis Kratsios, Cody B. Hyndman:
Generative Ornstein-Uhlenbeck Markets via Geometric Deep Learning. CoRR abs/2302.09176 (2023) - [i20]Anastasis Kratsios, Chong Liu, Matti Lassas, Maarten V. de Hoop, Ivan Dokmanic:
A Transfer Principle: Universal Approximators Between Metric Spaces From Euclidean Universal Approximators. CoRR abs/2304.12231 (2023) - [i19]Anastasis Kratsios, Ruiyang Hong, Haitz Sáez de Ocáriz Borde:
Capacity Bounds for Hyperbolic Neural Network Representations of Latent Tree Structures. CoRR abs/2308.09250 (2023) - [i18]Xuwei Yang, Anastasis Kratsios, Florian Krach, Matheus R. Grasselli, Aurélien Lucchi:
Regret-Optimal Federated Transfer Learning for Kernel Regression with Applications in American Option Pricing. CoRR abs/2309.04557 (2023) - [i17]Tin Sum Cheng, Aurélien Lucchi, Ivan Dokmanic, Anastasis Kratsios, David Belius:
A Theoretical Analysis of the Test Error of Finite-Rank Kernel Ridge Regression. CoRR abs/2310.00987 (2023) - [i16]Haitz Sáez de Ocáriz Borde, Anastasis Kratsios:
Neural Snowflakes: Universal Latent Graph Inference via Trainable Latent Geometries. CoRR abs/2310.15003 (2023) - [i15]Blanka Hovart, Anastasis Kratsios, Yannick Limmer, Xuwei Yang:
Deep Kalman Filters Can Filter. CoRR abs/2310.19603 (2023) - 2022
- [j5]Anastasis Kratsios, Behnoosh Zamanlooy:
Learning sub-patterns in piecewise continuous functions. Neurocomputing 480: 192-211 (2022) - [j4]Anastasis Kratsios, Leonie Papon:
Universal Approximation Theorems for Differentiable Geometric Deep Learning. J. Mach. Learn. Res. 23: 196:1-196:73 (2022) - [j3]Anastasis Kratsios, Behnoosh Zamanlooy:
Do ReLU Networks Have An Edge When Approximating Compactly-Supported Functions? Trans. Mach. Learn. Res. 2022 (2022) - [c4]Anastasis Kratsios, Behnoosh Zamanlooy, Tianlin Liu, Ivan Dokmanic:
Universal Approximation Under Constraints is Possible with Transformers. ICLR 2022 - [i14]Beatrice Acciaio, Anastasis Kratsios, Gudmund Pammer:
Metric Hypertransformers are Universal Adapted Maps. CoRR abs/2201.13094 (2022) - [i13]Anastasis Kratsios, Behnoosh Zamanlooy:
Piecewise-Linear Activations or Analytic Activation Functions: Which Produce More Expressive Neural Networks? CoRR abs/2204.11231 (2022) - [i12]Anastasis Kratsios, Valentin Debarnot, Ivan Dokmanic:
Small Transformers Compute Universal Metric Embeddings. CoRR abs/2209.06788 (2022) - [i11]Luca Galimberti, Giulia Livieri, Anastasis Kratsios:
Designing Universal Causal Deep Learning Models: The Case of Infinite-Dimensional Dynamical Systems from Stochastic Analysis. CoRR abs/2210.13300 (2022) - [i10]Songyan Hou, Parnian Kassraie, Anastasis Kratsios, Jonas Rothfuss, Andreas Krause:
Instance-Dependent Generalization Bounds via Optimal Transport. CoRR abs/2211.01258 (2022) - 2021
- [j2]Anastasis Kratsios:
The Universal Approximation Property. Ann. Math. Artif. Intell. 89(5-6): 435-469 (2021) - [j1]Anastasis Kratsios, Cody B. Hyndman:
NEU: A Meta-Algorithm for Universal UAP-Invariant Feature Representation. J. Mach. Learn. Res. 22: 92:1-92:51 (2021) - [c3]Philippe Casgrain, Anastasis Kratsios:
Optimizing Optimizers: Regret-optimal gradient descent algorithms. COLT 2021: 883-926 - [c2]Anastasis Kratsios, Cody B. Hyndman:
Generative OrnsteinUhlenbeck Markets via Geometric Deep Learning. GSI (2) 2021: 605-614 - [i9]Philippe Casgrain, Anastasis Kratsios:
Optimizing Optimizers: Regret-optimal gradient descent algorithms. CoRR abs/2101.00041 (2021) - [i8]Anastasis Kratsios, Leonie Papon:
Quantitative Rates and Fundamental Obstructions to Non-Euclidean Universal Approximation with Deep Narrow Feed-Forward Networks. CoRR abs/2101.05390 (2021) - [i7]Anastasis Kratsios:
Universal Regular Conditional Distributions via Probability Measure-Valued Deep Neural Models. CoRR abs/2105.07743 (2021) - [i6]Anastasis Kratsios, Behnoosh Zamanlooy, Tianlin Liu, Ivan Dokmanic:
Universal Approximation Under Constraints is Possible with Transformers. CoRR abs/2110.03303 (2021) - 2020
- [c1]Anastasis Kratsios, Ievgen Bilokopytov:
Non-Euclidean Universal Approximation. NeurIPS 2020 - [i5]Anastasis Kratsios, Ievgen Bilokopytov:
Non-Euclidean Universal Approximation. CoRR abs/2006.02341 (2020) - [i4]Anastasis Kratsios, Behnoosh Zamanlooy:
Architopes: An Architecture Modification for Composite Pattern Learning, Increased Expressiveness, and Reduced Training Time. CoRR abs/2006.14378 (2020) - [i3]Anastasis Kratsios, Behnoosh Zamanlooy:
Overcoming The Limitations of Neural Networks in Composite-Pattern Learning with Architopes. CoRR abs/2010.15571 (2020)
2010 – 2019
- 2019
- [i2]Anastasis Kratsios:
Universal Approximation Theorems. CoRR abs/1910.03344 (2019) - 2018
- [i1]Anastasis Kratsios, Cody B. Hyndman:
The NEU Meta-Algorithm for Geometric Learning with Applications in Finance. CoRR abs/1809.00082 (2018)
Coauthor Index
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
Unpaywalled article links
Add open access links from 
to the list of external document links (if available).
Privacy notice: By enabling the option above, your browser will contact the API of unpaywall.org to load hyperlinks to open access articles. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Unpaywall privacy policy.
Archived links via Wayback Machine
For web page which are no longer available, try to retrieve content from the 
of the Internet Archive (if available).
Privacy notice: By enabling the option above, your browser will contact the API of archive.org to check for archived content of web pages that are no longer available. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Internet Archive privacy policy.
Reference lists
Add a list of references from 
, 
, and 
to record detail pages.
load references from crossref.org and opencitations.net
Privacy notice: By enabling the option above, your browser will contact the APIs of crossref.org, opencitations.net, and semanticscholar.org to load article reference information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Crossref privacy policy and the OpenCitations privacy policy, as well as the AI2 Privacy Policy covering Semantic Scholar.
Citation data
Add a list of citing articles from and to record detail pages.
load citations from opencitations.net
Privacy notice: By enabling the option above, your browser will contact the API of opencitations.net and semanticscholar.org to load citation information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the OpenCitations privacy policy as well as the AI2 Privacy Policy covering Semantic Scholar.
OpenAlex data
Load additional information about publications from 
.
Privacy notice: By enabling the option above, your browser will contact the API of openalex.org to load additional information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the information given by OpenAlex.
last updated on 2025-01-09 13:09 CET by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by:
