Copertina

Stochastic Gradient Flow Dynamics of Test Risk and its Exact Solution for Weak Features

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Veiga, Rodrigo, Remizova, Anastasia, Macris, Nicolas
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Machine Learning Disordered Systems and Neural Networks
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Analysis of Diffusion Models for Manifold Data
di: George, Anand Jerry, et al.
Pubblicazione: (2025)

High-Dimensional Limit of Stochastic Gradient Flow via Dynamical Mean-Field Theory
di: Nishiyama, Sota, et al.
Pubblicazione: (2026)

Two-Point Deterministic Equivalence for Stochastic Gradient Dynamics in Linear Models
di: Atanasov, Alexander, et al.
Pubblicazione: (2025)

On the different regimes of Stochastic Gradient Descent
di: Sclocchi, Antonio, et al.
Pubblicazione: (2023)

Transient learning dynamics drive escape from sharp valleys in Stochastic Gradient Descent
di: Yang, Ning, et al.
Pubblicazione: (2026)

Anti-Correlated Noise in Epoch-Based Stochastic Gradient Descent: Implications for Weight Variances in Flat Directions
di: Kühn, Marcel, et al.
Pubblicazione: (2023)

Growing Neural Networks: Dynamic Evolution through Gradient Descent
di: Radhakrishnan, Anil, et al.
Pubblicazione: (2025)

Exact Learning Dynamics of In-Context Learning in Linear Transformers and Its Application to Non-Linear Transformers
di: Mainali, Nischal, et al.
Pubblicazione: (2025)

Stochastic Interpolants: A Unifying Framework for Flows and Diffusions
di: Albergo, Michael S., et al.
Pubblicazione: (2023)

Exact Fixed-Point Constraints in Neural-ODEs with Provable Universality
di: Pacifico, Feliciano Giuseppe, et al.
Pubblicazione: (2026)

Class Imbalance in Anomaly Detection: Learning from an Exactly Solvable Model
di: Pezzicoli, F. S., et al.
Pubblicazione: (2025)

The committee machine: Computational to statistical gaps in learning a two-layers neural network
di: Aubin, Benjamin, et al.
Pubblicazione: (2018)

From Kernels to Features: A Multi-Scale Adaptive Theory of Feature Learning
di: Rubin, Noa, et al.
Pubblicazione: (2025)

Convergence Acceleration of Markov Chain Monte Carlo-based Gradient Descent by Deep Unfolding
di: Hagiwara, Ryo, et al.
Pubblicazione: (2024)

Transfer Learning in Infinite Width Feature Learning Networks
di: Lauditi, Clarissa, et al.
Pubblicazione: (2025)

How Feature Learning Can Improve Neural Scaling Laws
di: Bordelon, Blake, et al.
Pubblicazione: (2024)

Risk and cross validation in ridge regression with correlated samples
di: Atanasov, Alexander, et al.
Pubblicazione: (2024)

Solution space and storage capacity of fully connected two-layer neural networks with generic activation functions
di: Nishiyama, Sota, et al.
Pubblicazione: (2024)

Stochastic Gradient Descent-like relaxation is equivalent to Metropolis dynamics in discrete optimization and inference problems
di: Angelini, Maria Chiara, et al.
Pubblicazione: (2023)

High-Dimensional Analysis of Gradient Flow for Extensive-Width Quadratic Neural Networks
di: Martin, Simon, et al.
Pubblicazione: (2026)

No Free Lunch From Random Feature Ensembles: Scaling Laws and Near-Optimality Conditions
di: Ruben, Benjamin S., et al.
Pubblicazione: (2024)

Theory of Optimal Learning Rate Schedules and Scaling Laws for a Random Feature Model
di: Bordelon, Blake, et al.
Pubblicazione: (2026)

Statistical Physics of Deep Neural Networks: Generalization Capability, Beyond the Infinite Width, and Feature Learning
di: Ariosto, Sebastiano
Pubblicazione: (2025)

Deep Learning as Neural Low-Degree Filtering: A Spectral Theory of Hierarchical Feature Learning
di: Dandi, Yatin, et al.
Pubblicazione: (2026)

Precise Dynamics of Diagonal Linear Networks: A Unifying Analysis by Dynamical Mean-Field Theory
di: Nishiyama, Sota, et al.
Pubblicazione: (2025)

Topological Exploration of High-Dimensional Empirical Risk Landscapes: general approach, and applications to phase retrieval
di: Maillard, Antoine, et al.
Pubblicazione: (2026)

Dynamical Regimes of Multimodal Diffusion Models
di: Albrychiewicz, Emil, et al.
Pubblicazione: (2026)

Infinite Limits of Multi-head Transformer Dynamics
di: Bordelon, Blake, et al.
Pubblicazione: (2024)

A Dynamical Model of Neural Scaling Laws
di: Bordelon, Blake, et al.
Pubblicazione: (2024)

Exact full-RSB SAT/UNSAT transition in infinitely wide two-layer neural networks
di: Annesi, Brandon L., et al.
Pubblicazione: (2024)

Geometric Dynamics of Signal Propagation Predict Trainability of Transformers
di: Cowsik, Aditya, et al.
Pubblicazione: (2024)

Dynamics of Meta-learning Representation in the Teacher-student Scenario
di: Wang, Hui, et al.
Pubblicazione: (2024)

Grokking as the Transition from Lazy to Rich Training Dynamics
di: Kumar, Tanishq, et al.
Pubblicazione: (2023)

Bias in Motion: Theoretical Insights into the Dynamics of Bias in SGD Training
di: Jain, Anchit, et al.
Pubblicazione: (2024)

Dynamical Mean-Field Theory of Self-Attention Neural Networks
di: Poc-López, Ángel, et al.
Pubblicazione: (2024)

The RL Perceptron: Generalisation Dynamics of Policy Learning in High Dimensions
di: Patel, Nishil, et al.
Pubblicazione: (2023)

The Interplay of Data Structure and Imbalance in the Learning Dynamics of Diffusion Models
di: Nicoletti, Flavio, et al.
Pubblicazione: (2026)

Dynamical Decoupling of Generalization and Overfitting in Large Two-Layer Networks
di: Montanari, Andrea, et al.
Pubblicazione: (2025)

Training Dynamics of Nonlinear Contrastive Learning Model in the High Dimensional Limit
di: Meng, Lineghuan, et al.
Pubblicazione: (2024)

Disordered Dynamics in High Dimensions: Connections to Random Matrices and Machine Learning
di: Bordelon, Blake, et al.
Pubblicazione: (2026)