Cover Image

Don't Stop Me Yet: Sampling Loss Minima via Dissipative Riemannian Mechanics

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Jacobsen, Albert Kjøller, Jakobsen, Leo Uhre, Gegenfurtner, Johanna Marie, Arvanitidis, Georgios
Format:	Preprint
Published:	2026
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Staying on the Manifold: Geometry-Aware Noise Injection
by: Jacobsen, Albert Kjøller, et al.
Published: (2025)

Reducing Memorisation in Generative Models via Riemannian Bayesian Inference
by: Gegenfurtner, Johanna Marie, et al.
Published: (2026)

Monge SAM: Robust Reparameterization-Invariant Sharpness-Aware Minimization Based on Loss Geometry
by: Jacobsen, Albert Kjøller, et al.
Published: (2025)

Don't Stop Me Now: Embedding Based Scheduling for LLMs
by: Shahout, Rana, et al.
Published: (2024)

Counterfactual Explanations via Riemannian Latent Space Traversal
by: Pegios, Paraskevas, et al.
Published: (2024)

Minimal Submanifolds of the Classical Compact Riemannian Symmetric Spaces
by: Gegenfurtner, Johanna Marie
Published: (2024)

Extended Neural Contractive Dynamical Systems: On Multiple Tasks and Riemannian Safety Regions
by: Mohammadi, Hadi Beik, et al.
Published: (2024)

Don't Waste Your Time: Early Stopping Cross-Validation
by: Bergman, Edward, et al.
Published: (2024)

Show Me What You Don't Know: Efficient Sampling from Invariant Sets for Model Validation
by: Rousselot, Armand, et al.
Published: (2026)

The Symmetries of Three-Layer ReLU Networks
by: Gegenfurtner, Johanna Marie, et al.
Published: (2026)

How Redundant Is the Transformer Stack in Speech Representation Models?
by: Dorszewski, Teresa, et al.
Published: (2024)

Don't Fool Me Twice: Adapting to Adversity in the Wild with Experience-Driven Reasoning
by: Ravie, Navin Sriram, et al.
Published: (2026)

Learning Geometry and Topology via Multi-Chart Flows
by: Yu, Hanlin, et al.
Published: (2025)

LoRA and Privacy: When Random Projections Help (and When They Don't)
by: Hu, Yaxi, et al.
Published: (2026)

Experts Don't Cheat: Learning What You Don't Know By Predicting Pairs
by: Johnson, Daniel D., et al.
Published: (2024)

Ignore Me But Don't Replace Me: Utilizing Non-Linguistic Elements for Pretraining on the Cybersecurity Domain
by: Jang, Eugene, et al.
Published: (2024)

Nexus: Same Pretraining Loss, Better Downstream Generalization via Common Minima
by: Chen, Huanran, et al.
Published: (2026)

Sample, Don't Search: Rethinking Test-Time Alignment for Language Models
by: Faria, Gonçalo, et al.
Published: (2025)

A Runway to Dissipation of Angular Momentum via Worldline Quantum Field Theory
by: Jakobsen, Gustav Uhre, et al.
Published: (2026)

Compact minimal submanifolds of the Riemannian symmetric spaces $SU(n)/SO(n)$, $Sp(n)/U(n)$, $SO(2n)/U(n)$, $SU(2n)/Sp(n)$ via complex-valued eigenfunctions
by: Gegenfurtner, Johanna Marie, et al.
Published: (2024)

If You Don't Understand It, Don't Use It: Eliminating Trojans with Filters Between Layers
by: Hernandez, Adriano
Published: (2024)

Don't Get Me Wrong: How to Apply Deep Visual Interpretations to Time Series
by: Loeffler, Christoffer, et al.
Published: (2022)

Don't Mesh with Me: Generating Constructive Solid Geometry Instead of Meshes by Fine-Tuning a Code-Generation LLM
by: Mews, Maximilian, et al.
Published: (2024)

Don't Freeze, Don't Crash: Extending the Safe Operating Range of Neural Navigation in Dense Crowds
by: Zhang, Jiefu, et al.
Published: (2026)

Sharp Minima Can Generalize: A Loss Landscape Perspective On Data
by: Fan, Raymond, et al.
Published: (2025)

Don't Waste Mistakes: Leveraging Negative RL-Groups via Confidence Reweighting
by: Feng, Yunzhen, et al.
Published: (2025)

Connecting Neural Models Latent Geometries with Relative Geodesic Representations
by: Yu, Hanlin, et al.
Published: (2025)

Geodesic Slice Sampler for Multimodal Distributions with Strong Curvature
by: Williams, Bernardo, et al.
Published: (2025)

Position: Don't be Afraid of Over-Smoothing And Over-Squashing
by: Kormann, Niklas, et al.
Published: (2026)

When Models Don't Collapse: On the Consistency of Iterative MLE
by: Barzilai, Daniel, et al.
Published: (2025)

Grow, Don't Overwrite: Fine-tuning Without Forgetting
by: Adila, Dyah, et al.
Published: (2026)

Don't Pay Attention, PLANT It: Pretraining Attention via Learning-to-Rank
by: Roy, Debjyoti Saha, et al.
Published: (2024)

Don't Be Greedy, Just Relax! Pruning LLMs via Frank-Wolfe
by: Roux, Christophe, et al.
Published: (2025)

Attention Mechanisms Don't Learn Additive Models: Rethinking Feature Importance for Transformers
by: Leemann, Tobias, et al.
Published: (2024)

Minima and Critical Points of the Bethe Free Energy Are Invariant Under Deformation Retractions of Factor Graphs
by: Sergeant-Perthuis, Grégoire, et al.
Published: (2025)

We Still Don't Understand High-Dimensional Bayesian Optimization
by: Doumont, Colin, et al.
Published: (2025)

Don't Forget Imagination!
by: Vityaev, Evgenii E., et al.
Published: (2025)

GRADSTOP: Early Stopping of Gradient Descent via Posterior Sampling
by: Jamshidi, Arash, et al.
Published: (2025)

Don't Explain Noise: Robust Counterfactuals for Randomized Ensembles
by: Forel, Alexandre, et al.
Published: (2022)

Transformers Don't In-Context Learn Least Squares Regression
by: Hill, Joshua, et al.
Published: (2025)