Copertina

Learning Multi-Index Models with Neural Networks via Mean-Field Langevin Dynamics

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Mousavi-Hosseini, Alireza, Wu, Denny, Erdogdu, Murat A.
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Robust Feature Learning for Multi-Index Models in High Dimensions
di: Mousavi-Hosseini, Alireza, et al.
Pubblicazione: (2024)

When Do Transformers Outperform Feedforward and Recurrent Networks? A Statistical Perspective
di: Mousavi-Hosseini, Alireza, et al.
Pubblicazione: (2025)

Post-Training with Policy Gradients: Optimality and the Base Model Barrier
di: Mousavi-Hosseini, Alireza, et al.
Pubblicazione: (2026)

Mean-Field Langevin Dynamics for Signed Measures via a Bilevel Approach
di: Wang, Guillaume, et al.
Pubblicazione: (2024)

From Information to Generative Exponent: Learning Rate Induces Phase Transitions in SGD
di: Tsiolis, Konstantinos Christopher, et al.
Pubblicazione: (2025)

A Separation in Heavy-Tailed Sampling: Gaussian vs. Stable Oracles for Proximal Samplers
di: He, Ye, et al.
Pubblicazione: (2024)

Learning quadratic neural networks in high dimensions: SGD dynamics and scaling laws
di: Arous, Gérard Ben, et al.
Pubblicazione: (2025)

Sampling from the Mean-Field Stationary Distribution
di: Kook, Yunbum, et al.
Pubblicazione: (2024)

Pruning is Optimal for Learning Sparse Features in High-Dimensions
di: Vural, Nuri Mert, et al.
Pubblicazione: (2024)

Analysis of Langevin Monte Carlo from Poincaré to Log-Sobolev
di: Chewi, Sinho, et al.
Pubblicazione: (2021)

Thinned Mean Field Langevin Dynamics
di: Chen, Zonghao, et al.
Pubblicazione: (2026)

Mirror Mean-Field Langevin Dynamics
di: Gu, Anming, et al.
Pubblicazione: (2025)

Optimal Excess Risk Bounds for Empirical Risk Minimization on $p$-Norm Linear Regression
di: Hanchi, Ayoub El, et al.
Pubblicazione: (2023)

Propagation of Chaos for Mean-Field Langevin Dynamics and its Application to Model Ensemble
di: Nitanda, Atsushi, et al.
Pubblicazione: (2025)

Private Continuous-Time Synthetic Trajectory Generation via Mean-Field Langevin Dynamics
di: Gu, Anming, et al.
Pubblicazione: (2025)

On the Efficiency of ERM in Feature Learning
di: Hanchi, Ayoub El, et al.
Pubblicazione: (2024)

On Fitting Flow Models with Large Sinkhorn Couplings
di: Zhang, Stephen, et al.
Pubblicazione: (2025)

A Geometric Analysis of PCA
di: Hanchi, Ayoub El, et al.
Pubblicazione: (2025)

Minimax Linear Regression under the Quantile Risk
di: Hanchi, Ayoub El, et al.
Pubblicazione: (2024)

Beyond Labeling Oracles: What does it mean to steal ML models?
di: Shafran, Avital, et al.
Pubblicazione: (2023)

Neural Collapse Beyond the Unconstrained Features Model: Landscape, Dynamics, and Generalization in the Mean-Field Regime
di: Wu, Diyuan, et al.
Pubblicazione: (2025)

Flow Matching with Semidiscrete Couplings
di: Mousavi-Hosseini, Alireza, et al.
Pubblicazione: (2025)

Langevin Flows for Modeling Neural Latent Dynamics
di: Song, Yue, et al.
Pubblicazione: (2025)

Propagation of Chaos in One-hidden-layer Neural Networks beyond Logarithmic Time
di: Glasgow, Margalit, et al.
Pubblicazione: (2025)

Adaptive Stepsizing for Stochastic Gradient Langevin Dynamics in Bayesian Neural Networks
di: Rajpal, Rajit, et al.
Pubblicazione: (2025)

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

Symmetric Mean-field Langevin Dynamics for Distributional Minimax Problems
di: Kim, Juno, et al.
Pubblicazione: (2023)

Learning Latent Energy-Based Models via Interacting Particle Langevin Dynamics
di: Marks, Joanna, et al.
Pubblicazione: (2025)

Improved Particle Approximation Error for Mean Field Neural Networks
di: Nitanda, Atsushi
Pubblicazione: (2024)

BACE: Behavior-Adaptive Connectivity Estimation for Interpretable Graphs of Neural Dynamics
di: Asadi, Mehrnaz, et al.
Pubblicazione: (2025)

Imposing Boundary Conditions on Neural Operators via Learned Function Extensions
di: Mousavi, Sepehr, et al.
Pubblicazione: (2026)

Controlled Langevin Dynamics for Sampling of Feedforward Neural Networks Trained with Minibatches
di: Zambon, Alessandro, et al.
Pubblicazione: (2026)

Full-Batch Gradient Descent Outperforms One-Pass SGD: Sample Complexity Separation in Single-Index Learning
di: Kovačević, Filip, et al.
Pubblicazione: (2026)

Symmetries in Overparametrized Neural Networks: A Mean-Field View
di: Maass, Javier, et al.
Pubblicazione: (2024)

Microcanonical Langevin Ensembles: Advancing the Sampling of Bayesian Neural Networks
di: Sommer, Emanuel, et al.
Pubblicazione: (2025)

Efficient Relation-aware Neighborhood Aggregation in Graph Neural Networks via Tensor Decomposition
di: Baghershahi, Peyman, et al.
Pubblicazione: (2022)

On the Robustness of Langevin Dynamics to Score Function Error
di: Cao, Daniel Yiming, et al.
Pubblicazione: (2026)

Sampling from Bayesian Neural Network Posteriors with Symmetric Minibatch Splitting Langevin Dynamics
di: Paulin, Daniel, et al.
Pubblicazione: (2024)

Mean-Field Langevin Diffusions with Density-dependent Temperature
di: Huang, Yu-Jui, et al.
Pubblicazione: (2025)

On the Hardness of Sampling from Mixture Distributions via Langevin Dynamics
di: Cheng, Xiwei, et al.
Pubblicazione: (2024)