Cover Image

The Expected Loss of Preconditioned Langevin Dynamics Reveals the Hessian Rank

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Bar, Amitay, Mulayoff, Rotem, Michaeli, Tomer, Talmon, Ronen
Format:	Preprint
Published:	2024
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Exact Mean Square Linear Stability Analysis for SGD
by: Mulayoff, Rotem, et al.
Published: (2023)

Hierarchical Uncertainty Exploration via Feedforward Posterior Trees
by: Nehme, Elias, et al.
Published: (2024)

On Interference-Rejection Using Riemannian Geometry for Direction of Arrival Estimation
by: Bar, Amitay, et al.
Published: (2023)

On the Stability of Nonlinear Dynamics in GD and SGD: Beyond Quadratic Potentials
by: Mulayoff, Rotem, et al.
Published: (2026)

Discovering Interpretable Directions in the Semantic Latent Space of Diffusion Models
by: Haas, René, et al.
Published: (2023)

Riemannian Covariance Fitting for Direction-of-Arrival Estimation
by: Picard, Joseph S., et al.
Published: (2024)

LoRA vs. Full Fine-Tuning: A Theoretical Perspective
by: Zindari, Ali, et al.
Published: (2026)

Domain Adaptation for DoA Estimation in Multipath Channels with Interferences
by: Bar, Amitay, et al.
Published: (2024)

Learning When to Adapt
by: Zindari, Ali, et al.
Published: (2026)

It Takes a Graph to Know a Graph: Rewiring for Homophily with a Reference Graph
by: Mendelman, Harel, et al.
Published: (2025)

Time-Inhomogeneous Preconditioned Langevin Dynamics
by: Falk, Alexander, et al.
Published: (2026)

Coherence Awareness in Diffractive Neural Networks
by: Kleiner, Matan, et al.
Published: (2024)

Illumination Angular Spectrum Encoding for Controlling the Functionality of Diffractive Networks
by: Kleiner, Matan, et al.
Published: (2026)

Complex Interpolation of Matrices with an application to Multi-Manifold Learning
by: Arbel, Adi, et al.
Published: (2026)

Zero-Shot Unsupervised and Text-Based Audio Editing Using DDPM Inversion
by: Manor, Hila, et al.
Published: (2024)

On the Posterior Distribution in Denoising: Application to Uncertainty Quantification
by: Manor, Hila, et al.
Published: (2023)

Enhancing VICReg: Random-Walk Pairing for Improved Generalization and Better Global Semantics Capturing
by: Simai, Idan, et al.
Published: (2025)

Classification Diffusion Models: Revitalizing Density Ratio Estimation
by: Yadin, Shahar, et al.
Published: (2024)

Joint auto-encoders: a flexible multi-task learning framework
by: Epstein, Baruch, et al.
Published: (2017)

Equivariant Machine Learning on Graphs with Nonlinear Spectral Filters
by: Lin, Ya-Wei Eileen, et al.
Published: (2024)

FlowOpt: Fast Optimization Through Whole Flow Processes for Training-Free Editing
by: Ronai, Or, et al.
Published: (2025)

Docking-Aware Attention: Dynamic Protein Representations through Molecular Context Integration
by: Sicherman, Amitay, et al.
Published: (2025)

SINR-Aware Deep Reinforcement Learning for Distributed Dynamic Channel Allocation in Cognitive Interference Networks
by: Cohen, Yaniv, et al.
Published: (2024)

Tree-Wasserstein Distance for High Dimensional Data with a Latent Feature Hierarchy
by: Lin, Ya-Wei Eileen, et al.
Published: (2024)

Joint Hierarchical Representation Learning of Samples and Features via Informed Tree-Wasserstein Distance
by: Lin, Ya-Wei Eileen, et al.
Published: (2025)

An Edit Friendly DDPM Noise Space: Inversion and Manipulations
by: Huberman-Spiegelglas, Inbar, et al.
Published: (2023)

Adaptive Compressed Sensing with Diffusion-Based Posterior Sampling
by: Elata, Noam, et al.
Published: (2024)

Learning Shared Representations from Unpaired Data
by: Yacobi, Amitai, et al.
Published: (2025)

Perceptual Fairness in Image Restoration
by: Ohayon, Guy, et al.
Published: (2024)

The Perception-Robustness Tradeoff in Deterministic Image Restoration
by: Ohayon, Guy, et al.
Published: (2023)

ReactEmbed: A Plug-and-Play Module for Unifying Protein-Molecule Representations Guided by Biochemical Reaction Networks
by: Sicherman, Amitay, et al.
Published: (2025)

FlowEdit: Inversion-Free Text-Based Editing Using Pre-Trained Flow Models
by: Kulikov, Vladimir, et al.
Published: (2024)

Multiplicative Reweighting for Robust Neural Network Optimization
by: Bar, Noga, et al.
Published: (2021)

When Diffusion Models Memorize: Inductive Biases in Probability Flow of Minimum-Norm Shallow Neural Nets
by: Zeno, Chen, et al.
Published: (2025)

Reasons for the Superiority of Stochastic Estimators over Deterministic Ones: Robustness, Consistency and Perceptual Quality
by: Ohayon, Guy, et al.
Published: (2022)

From Posterior Sampling to Meaningful Diversity in Image Restoration
by: Cohen, Noa, et al.
Published: (2023)

GSURE-Based Diffusion Model Training with Corrupted Data
by: Kawar, Bahjat, et al.
Published: (2023)

Multiclass Loss Geometry Matters for Generalization of Gradient Descent in Separable Classification
by: Schliserman, Matan, et al.
Published: (2025)

High-accuracy sampling from constrained spaces with the Metropolis-adjusted Preconditioned Langevin Algorithm
by: Srinivasan, Vishwak, et al.
Published: (2024)

Generalizing Linear Autoencoder Recommenders with Decoupled Expected Quadratic Loss
by: Guo, Ruixin, et al.
Published: (2026)