Imagen de Portada

Sharp Generalization Bounds for Foundation Models with Asymmetric Randomized Low-Rank Adapters

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Kratsios, Anastasis, Cheng, Tin Sum, Lucchi, Aurelien, Borde, Haitz Sáez de Ocáriz
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning Artificial Intelligence Neural and Evolutionary Computing Statistics Theory
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Neural Snowflakes: Universal Latent Graph Inference via Trainable Latent Geometries
por: Borde, Haitz Sáez de Ocáriz, et al.
Publicado: (2023)

Approximation Rates and VC-Dimension Bounds for (P)ReLU MLP Mixture of Experts
por: Kratsios, Anastasis, et al.
Publicado: (2024)

Keep It Light! Simplifying Image Clustering Via Text-Free Adapters
por: Li, Yicen, et al.
Publicado: (2025)

Every Feedforward Neural Network Definable in an o-Minimal Structure Has Finite Sample Complexity
por: Kratsios, Anastasis, et al.
Publicado: (2026)

Neural Spacetimes for DAG Representation Learning
por: Borde, Haitz Sáez de Ocáriz, et al.
Publicado: (2024)

Statistical Guarantees for Reasoning Probes on Looped Boolean Circuits
por: Kratsios, Anastasis, et al.
Publicado: (2026)

Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data
por: Kratsios, Anastasis, et al.
Publicado: (2025)

Is In-Context Universality Enough? MLPs are Also Universal In-Context
por: Kratsios, Anastasis, et al.
Publicado: (2025)

Approximation Rates in Besov Norms and Sample-Complexity of Kolmogorov-Arnold Networks with Residual Connections
por: Kratsios, Anastasis, et al.
Publicado: (2025)

Probabilistic computation and uncertainty quantification with emerging covariance
por: Ma, Hengyuan, et al.
Publicado: (2023)

LoRA Fine-Tuning Without GPUs: A CPU-Efficient Meta-Generation Framework for LLMs
por: Arabpour, Reza, et al.
Publicado: (2025)

Generative thermodynamic computing
por: Whitelam, Stephen
Publicado: (2025)

Low-dimensional approximations of the conditional law of Volterra processes: a non-positive curvature approach
por: Arabpour, Reza, et al.
Publicado: (2024)

Bridging the Gap Between Approximation and Learning via Optimal Approximation by ReLU MLPs of Maximal Regularity
por: Hong, Ruiyang, et al.
Publicado: (2024)

Algebraic Statistics in OSCAR
por: Boege, Tobias, et al.
Publicado: (2026)

ForwardFlow: Simulation only statistical inference using deep learning
por: Böhringer, Stefan
Publicado: (2026)

Thermodynamics of bidirectional associative memories
por: Barra, Adriano, et al.
Publicado: (2022)

Structure-Preserving Reconstruction of Convex Lipschitz Functionals on Hilbert Spaces from Finite Samples
por: Kratsios, Anastasis
Publicado: (2026)

A Little Rank Goes a Long Way: Random Scaffolds with LoRA Adapters Are All You Need
por: Hazan, Hananel, et al.
Publicado: (2026)

Gradient Projection onto Historical Descent Directions for Communication-Efficient Federated Learning
por: Descours, Arnaud, et al.
Publicado: (2025)

Uncertainty propagation through trained multi-layer perceptrons: Exact analytical results
por: Thompson, Andrew, et al.
Publicado: (2026)

Hierarchical Representations for Evolving Acyclic Vector Autoregressions (HEAVe)
por: Cornell, Cameron, et al.
Publicado: (2025)

Increasing the clock speed of a thermodynamic computer by adding noise
por: Whitelam, Stephen
Publicado: (2024)

Neural units with time-dependent functionality
por: Whitelam, Stephen
Publicado: (2024)

Evolutionary design of thermodynamic logic gates and their heat emission
por: Whitelam, Stephen
Publicado: (2026)

Low Rank Factorizations are Indirect Encodings for Deep Neuroevolution
por: Garbus, Jack, et al.
Publicado: (2025)

Characterizing Overfitting in Kernel Ridgeless Regression Through the Eigenspectrum
por: Cheng, Tin Sum, et al.
Publicado: (2024)

A Comprehensive Analysis on the Learning Curve in Kernel Ridge Regression
por: Cheng, Tin Sum, et al.
Publicado: (2024)

Pattern recognition in the nucleation kinetics of non-equilibrium self-assembly
por: Evans, Constantine Glen, et al.
Publicado: (2022)

A General Upper Bound for the Runtime of a Coevolutionary Algorithm on Impartial Combinatorial Games
por: Benford, Alistair, et al.
Publicado: (2024)

Quantized Approximately Orthogonal Recurrent Neural Networks
por: Foucault, Armand, et al.
Publicado: (2024)

Geometry-induced Regularization in Deep ReLU Neural Networks
por: Bona-Pellissier, Joachim, et al.
Publicado: (2024)

Towards Foundation Models for Consensus Rank Aggregation
por: Jin, Yijun, et al.
Publicado: (2026)

Maximum-Entropy Analog Computing Approaching ExaOPS-per-Watt Energy-efficiency at the RF-Edge
por: Undavalli, Aswin, et al.
Publicado: (2025)

Nonlinear thermodynamic computing out of equilibrium
por: Whitelam, Stephen, et al.
Publicado: (2024)

Multi-relational Graph Diffusion Neural Network with Parallel Retention for Stock Trends Classification
por: You, Zinuo, et al.
Publicado: (2024)

Designing a Dataset for Convolutional Neural Networks to Predict Space Groups Consistent with Extinction Laws
por: Wang, Hao, et al.
Publicado: (2024)

Alpha Mining and Enhancing via Warm Start Genetic Programming for Quantitative Investment
por: Ren, Weizhe, et al.
Publicado: (2024)

An optimization-based equilibrium measure describes non-equilibrium steady state dynamics: application to edge of chaos
por: Qiu, Junbin, et al.
Publicado: (2024)

A Quantum-Driven Evolutionary Framework for Solving High-Dimensional Sharpe Ratio Portfolio Optimization
por: Yu, Mingyang, et al.
Publicado: (2026)