Anastasis Kratsios

77 papers A* 10Journal 66Unranked 1

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Approximation rates in Besov norms and sample-complexity of Kolmogorov-Arnold networks with residual connections. Neural Networks Anastasis Kratsios, Bum Jun Kim, Takashi Furuya
2026	J	`jnl`	Certifiable Boolean Reasoning Is Universal. CoRR Wenhao Li, Anastasis Kratsios, Hrad Ghoukasian, Dennis Y. Zvigelsky
2026	J	`jnl`	Neural Operators Can Discover Functional Clusters. CoRR Yicen Li, Jose Antonio Lara Benitez, Ruiyang Hong, Anastasis Kratsios, Paul David McNicholas, Maarten V. de Hoop
2026	J	`jnl`	Statistical Guarantees for Reasoning Probes on Looped Boolean Circuits. CoRR Anastasis Kratsios, Giulia Livieri, A. Martina Neuman
2025	J	`jnl`	Approximation Rates and VC-Dimension Bounds for (P)ReLU MLP Mixture of Experts. Trans. Mach. Learn. Res. Anastasis Kratsios, Haitz Sáez de Ocáriz Borde, Takashi Furuya, Marc T. Law
2025	J	`jnl`	Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data. CoRR Anastasis Kratsios, Tin Sum Cheng, Daniel Roy
2025	A*	`conf`	Filtered not Mixed: Filtering-Based Online Gating for Mixture of Large Language Models. ICLR Raeid Saqur, Anastasis Kratsios, Florian Krach, Yannick Limmer, Blanka Horvath, Frank Rudzicz
2025	J	`jnl`	Generative Market Equilibrium Models with Stable Adversarial Learning via Reinforcement. CoRR Anastasis Kratsios, Xiaofei Shi, Qiang Sun, Zhanhao Zhang
2025	J	`jnl`	Generative Neural Operators of Log-Complexity Can Simultaneously Solve Infinitely Many Convex Programs. CoRR Anastasis Kratsios, Ariel Neufeld, Philipp Schmocker
2025	J	`jnl`	Guiding Two-Layer Neural Network Lipschitzness via Gradient Descent Learning Rate Constraints. CoRR Kyle Sung, Anastasis Kratsios, Noah Forman
2025	J	`jnl`	Incremental Generation is Necessary and Sufficient for Universality in Flow-Based Modelling. CoRR Hossein Rouhvarzi, Anastasis Kratsios
2025	J	`jnl`	Is In-Context Universality Enough? MLPs are Also Universal In-Context. CoRR Anastasis Kratsios, Takashi Furuya
2025	J	`jnl`	Keep It Light! Simplifying Image Clustering Via Text-Free Adapters. CoRR Yicen Li, Haitz Sáez de Ocáriz Borde, Anastasis Kratsios, Paul D. McNicholas
2025	J	`jnl`	Kolmogorov-Arnold Networks: Approximation and Learning Guarantees for Functions and their Derivatives. CoRR Anastasis Kratsios, Takashi Furuya
2025	J	`jnl`	Learning from one graph: transductive learning guarantees via the geometry of small random worlds. CoRR Nils Detering, Luca Galimberti, Anastasis Kratsios, Giulia Livieri, A. Martina Neuman
2025	J	`jnl`	LoRA Fine-Tuning Without GPUs: A CPU-Efficient Meta-Generation Framework for LLMs. CoRR Reza Arabpour, Haitz Sáez de Ocáriz Borde, Anastasis Kratsios
2025	J	`jnl`	Neural Operators Can Play Dynamic Stackelberg Games. J. Mach. Learn. Res. Guillermo A. Alvarez, Ibrahim Ekren, Anastasis Kratsios, Xuwei Yang
2025	A*	`conf`	Neural Spacetimes for DAG Representation Learning. ICLR Haitz Sáez de Ocáriz Borde, Anastasis Kratsios, Marc T. Law, Xiaowen Dong, Michael M. Bronstein
2025	J	`jnl`	One model to solve them all: 2BSDE families via neural operators. CoRR Takashi Furuya, Anastasis Kratsios, Dylan Possamaï, Bogdan Raonic
2025	J	`jnl`	Online Federation For Mixtures of Proprietary Agents with Black-Box Encoders. CoRR Xuwei Yang, Fatemeh Tavakoli, David B. Emerson, Anastasis Kratsios
2025	J	`jnl`	Quantifying The Limits of AI Reasoning: Systematic Neural Network Representations of Algorithms. CoRR Anastasis Kratsios, Dennis Y. Zvigelsky, Bradd Hart
2025	J	`jnl`	Sharp Generalization Bounds for Foundation Models with Asymmetric Randomized Low-Rank Adapters. CoRR Anastasis Kratsios, Tin Sum Cheng, Aurélien Lucchi, Haitz Sáez de Ocáriz Borde
2025	J	`jnl`	Simultaneously Solving Infinitely Many LQ Mean Field Games In Hilbert Spaces: The Power of Neural Operators. CoRR Dena Firoozi, Anastasis Kratsios, Xuwei Yang
2024	A*	`conf`	A Comprehensive Analysis on the Learning Curve in Kernel Ridge Regression. NeurIPS Tin Sum Cheng, Aurélien Lucchi, Anastasis Kratsios, David Belius
2024	J	`jnl`	A Comprehensive Analysis on the Learning Curve in Kernel Ridge Regression. CoRR Tin Sum Cheng, Aurélien Lucchi, Anastasis Kratsios, David Belius
2024	J	`jnl`	Breaking the Curse of Dimensionality with Distributed Neural Computation. CoRR Haitz Sáez de Ocáriz Borde, Takashi Furuya, Anastasis Kratsios, Marc T. Law
2024	J	`jnl`	Bridging the Gap Between Approximation and Learning via Optimal Approximation by ReLU MLPs of Maximal Regularity. CoRR Ruiyang Hong, Anastasis Kratsios
2024	J	`jnl`	Capacity bounds for hyperbolic neural network representations of latent tree structures. Neural Networks Anastasis Kratsios, Ruiyang Hong, Haitz Sáez de Ocáriz Borde
2024	A*	`conf`	Characterizing Overfitting in Kernel Ridgeless Regression Through the Eigenspectrum. ICML Tin Sum Cheng, Aurélien Lucchi, Anastasis Kratsios, David Belius
2024	J	`jnl`	Characterizing Overfitting in Kernel Ridgeless Regression Through the Eigenspectrum. CoRR Tin Sum Cheng, Aurélien Lucchi, Anastasis Kratsios, David Belius
2024	J	`jnl`	Digital Computers Break the Curse of Dimensionality: Adaptive Bounds via Finite Geometry. CoRR Anastasis Kratsios, A. Martina Neuman, Gudmund Pammer
2024	A*	`conf`	Energy-Guided Continuous Entropic Barycenter Estimation for General Costs. NeurIPS Alexander Kolesov, Petr Mokrov, Igor Udovichenko, Milena Gazdieva, Gudmund Pammer, Anastasis Kratsios, Evgeny Burnaev, Aleksandr Korotin
2024	J	`jnl`	Filtered not Mixed: Stochastic Filtering-Based Online Gating for Mixture of Large Language Models. CoRR Raeid Saqur, Anastasis Kratsios, Florian Krach, Yannick Limmer, Jacob-Junqi Tian, John Willes, Blanka Horvath, Frank Rudzicz
2024	J	`jnl`	Inverse Entropic Optimal Transport Solves Semi-supervised Learning via Data Likelihood Maximization. CoRR Mikhail Persiianov, Arip Asadulaev, Nikita Andreev, Nikita Starodubcev, Dmitry Baranchuk, Anastasis Kratsios, Evgeny Burnaev, Alexander Korotin
2024	J	`jnl`	Low-dimensional approximations of the conditional law of Volterra processes: a non-positive curvature approach. CoRR Reza Arabpour, John Armstrong, Luca Galimberti, Anastasis Kratsios, Giulia Livieri
2024	J	`jnl`	Mixture of Experts Soften the Curse of Dimensionality in Operator Learning. CoRR Anastasis Kratsios, Takashi Furuya, Jose Antonio Lara Benitez, Matti Lassas, Maarten V. de Hoop
2024	J	`jnl`	Neural Operators Can Play Dynamic Stackelberg Games. CoRR Guillermo A. Alvarez, Ibrahim Ekren, Anastasis Kratsios, Xuwei Yang
2024	A*	`conf`	Neural Snowflakes: Universal Latent Graph Inference via Trainable Latent Geometries. ICLR Haitz Sáez de Ocáriz Borde, Anastasis Kratsios
2024	J	`jnl`	Neural Spacetimes for DAG Representation Learning. CoRR Haitz Sáez de Ocáriz Borde, Anastasis Kratsios, Marc T. Law, Xiaowen Dong, Michael M. Bronstein
2024	J	`jnl`	Out-of-distributional risk bounds for neural operators with applications to the Helmholtz equation. J. Comput. Phys. Jose Antonio Lara Benitez, Takashi Furuya, Florian Faucher, Anastasis Kratsios, Xavier Tricoche, Maarten V. de Hoop
2024	J	`jnl`	Reality Only Happens Once: Single-Path Generalization Bounds for Transformers. CoRR Yannick Limmer, Anastasis Kratsios, Xuwei Yang, Raeid Saqur, Blanka Horvath
2024	J	`jnl`	Scalable Message Passing Neural Networks: No Need for Attention in Large Graph Representation Learning. CoRR Haitz Sáez de Ocáriz Borde, Artem Lukoianov, Anastasis Kratsios, Michael M. Bronstein, Xiaowen Dong
2024	J	`jnl`	Simultaneously Solving FBSDEs with Neural Operators of Logarithmic Depth, Constant Width, and Sub-Linear Rank. CoRR Takashi Furuya, Anastasis Kratsios
2023	A*	`conf`	A Theoretical Analysis of the Test Error of Finite-Rank Kernel Ridge Regression. NeurIPS Tin Sum Cheng, Aurélien Lucchi, Anastasis Kratsios, Ivan Dokmanic, David Belius
2023	J	`jnl`	A Theoretical Analysis of the Test Error of Finite-Rank Kernel Ridge Regression. CoRR Tin Sum Cheng, Aurélien Lucchi, Ivan Dokmanic, Anastasis Kratsios, David Belius
2023	J	`jnl`	A Transfer Principle: Universal Approximators Between Metric Spaces From Euclidean Universal Approximators. CoRR Anastasis Kratsios, Chong Liu, Matti Lassas, Maarten V. de Hoop, Ivan Dokmanic
2023	J	`jnl`	Capacity Bounds for Hyperbolic Neural Network Representations of Latent Tree Structures. CoRR Anastasis Kratsios, Ruiyang Hong, Haitz Sáez de Ocáriz Borde
2023	J	`jnl`	Deep Kalman Filters Can Filter. CoRR Blanka Hovart, Anastasis Kratsios, Yannick Limmer, Xuwei Yang
2023	J	`jnl`	Denise: Deep Robust Principal Component Analysis for Positive Semidefinite Matrices. Trans. Mach. Learn. Res. Calypso Herrera, Florian Krach, Anastasis Kratsios, Pierre Ruyssen, Josef Teichmann
2023	J	`jnl`	Generative Ornstein-Uhlenbeck Markets via Geometric Deep Learning. CoRR Anastasis Kratsios, Cody B. Hyndman
2023	J	`jnl`	Instance-Dependent Generalization Bounds via Optimal Transport. J. Mach. Learn. Res. Songyan Hou, Parnian Kassraie, Anastasis Kratsios, Andreas Krause, Jonas Rothfuss
2023	J	`jnl`	Neural Snowflakes: Universal Latent Graph Inference via Trainable Latent Geometries. CoRR Haitz Sáez de Ocáriz Borde, Anastasis Kratsios
2023	J	`jnl`	Regret-Optimal Federated Transfer Learning for Kernel Regression with Applications in American Option Pricing. CoRR Xuwei Yang, Anastasis Kratsios, Florian Krach, Matheus R. Grasselli, Aurélien Lucchi
2023	J	`jnl`	Small Transformers Compute Universal Metric Embeddings. J. Mach. Learn. Res. Anastasis Kratsios, Valentin Debarnot, Ivan Dokmanic
2022	J	`jnl`	Designing Universal Causal Deep Learning Models: The Case of Infinite-Dimensional Dynamical Systems from Stochastic Analysis. CoRR Luca Galimberti, Giulia Livieri, Anastasis Kratsios
2022	J	`jnl`	Do ReLU Networks Have An Edge When Approximating Compactly-Supported Functions? Trans. Mach. Learn. Res. Anastasis Kratsios, Behnoosh Zamanlooy
2022	J	`jnl`	Instance-Dependent Generalization Bounds via Optimal Transport. CoRR Songyan Hou, Parnian Kassraie, Anastasis Kratsios, Jonas Rothfuss, Andreas Krause
2022	J	`jnl`	Learning sub-patterns in piecewise continuous functions. Neurocomputing Anastasis Kratsios, Behnoosh Zamanlooy
2022	J	`jnl`	Metric Hypertransformers are Universal Adapted Maps. CoRR Beatrice Acciaio, Anastasis Kratsios, Gudmund Pammer
2022	J	`jnl`	Piecewise-Linear Activations or Analytic Activation Functions: Which Produce More Expressive Neural Networks? CoRR Anastasis Kratsios, Behnoosh Zamanlooy
2022	J	`jnl`	Small Transformers Compute Universal Metric Embeddings. CoRR Anastasis Kratsios, Valentin Debarnot, Ivan Dokmanic
2022	J	`jnl`	Universal Approximation Theorems for Differentiable Geometric Deep Learning. J. Mach. Learn. Res. Anastasis Kratsios, Leonie Papon
2022	A*	`conf`	Universal Approximation Under Constraints is Possible with Transformers. ICLR Anastasis Kratsios, Behnoosh Zamanlooy, Tianlin Liu, Ivan Dokmanic
2021	—	`conf`	Generative OrnsteinUhlenbeck Markets via Geometric Deep Learning. GSI (2) Anastasis Kratsios, Cody B. Hyndman
2021	J	`jnl`	NEU: A Meta-Algorithm for Universal UAP-Invariant Feature Representation. J. Mach. Learn. Res. Anastasis Kratsios, Cody B. Hyndman
2021	A*	`conf`	Optimizing Optimizers: Regret-optimal gradient descent algorithms. COLT Philippe Casgrain, Anastasis Kratsios
2021	J	`jnl`	Optimizing Optimizers: Regret-optimal gradient descent algorithms. CoRR Philippe Casgrain, Anastasis Kratsios
2021	J	`jnl`	Quantitative Rates and Fundamental Obstructions to Non-Euclidean Universal Approximation with Deep Narrow Feed-Forward Networks. CoRR Anastasis Kratsios, Leonie Papon
2021	J	`jnl`	The Universal Approximation Property. Ann. Math. Artif. Intell. Anastasis Kratsios
2021	J	`jnl`	Universal Approximation Under Constraints is Possible with Transformers. CoRR Anastasis Kratsios, Behnoosh Zamanlooy, Tianlin Liu, Ivan Dokmanic
2021	J	`jnl`	Universal Regular Conditional Distributions via Probability Measure-Valued Deep Neural Models. CoRR Anastasis Kratsios
2020	J	`jnl`	Architopes: An Architecture Modification for Composite Pattern Learning, Increased Expressiveness, and Reduced Training Time. CoRR Anastasis Kratsios, Behnoosh Zamanlooy
2020	A*	`conf`	Non-Euclidean Universal Approximation. NeurIPS Anastasis Kratsios, Ievgen Bilokopytov
2020	J	`jnl`	Non-Euclidean Universal Approximation. CoRR Anastasis Kratsios, Ievgen Bilokopytov
2020	J	`jnl`	Overcoming The Limitations of Neural Networks in Composite-Pattern Learning with Architopes. CoRR Anastasis Kratsios, Behnoosh Zamanlooy
2019	J	`jnl`	Universal Approximation Theorems. CoRR Anastasis Kratsios
2018	J	`jnl`	The NEU Meta-Algorithm for Geometric Learning with Applications in Finance. CoRR Anastasis Kratsios, Cody B. Hyndman