arXiv AI

Temporal Geometry of Deep Networks: Hyperbolic Representations of Training Dynamics for Intrinsic Explainability

arXiv Machine Learning

Jun 30

Scalar Representations of Neural Network Training Dynamics

arXiv:2606. 30384v1 Announce Type: new Abstract: Training in artificial neural networks can be viewed as a trajectory evolving through a high-dimensional loss landscape.

By Pedro Jim\'enez-Gonz\'alez, Miguel C. Soriano, Lucas Lacasa

rag

Hugging Face Trending Papers

Jun 29

Scalar Representations of Neural Network Training Dynamics

Training in artificial neural networks can be viewed as a trajectory evolving through a high-dimensional loss landscape. However, the large number of trainable parameters makes the direct analysis of these dynamics challenging.

rag

arXiv Machine Learning

Jun 17

A Dynamical Systems Perspective on the Analysis of Neural Networks

arXiv:2507. 05164v2 Announce Type: replace-cross Abstract: In this chapter, we utilize dynamical systems to analyze several aspects of machine learning algorithms.

By Dennis Chemnitz, Maximilian Engel, Christian Kuehn, Sara-Viola Kuntz

rag safety

arXiv Machine Learning

Sep 30

Traversing the solution space of neural networks with Hessian Null Space Continuation

arXiv:2609.38081v1 Announce Type: new Abstract: On a single task, deep networks can learn many solutions, depending on their optimizer, training data, architecture, and hyperparameters. Many of these...

By Ann Huang, Mitchell Ostrow, Zhouyang Lu, William T. Redman, Leo Kozachkov, Kanaka Rajan

llms agents fine-tuning safety

arXiv Machine Learning

Jul 13

How are linear representations learned? Exact solutions to the dynamics of abstraction

arXiv:2607. 08843v1 Announce Type: new Abstract: In artificial and biological neural networks, concepts are often encoded as consistent linear directions in representation space.

By William W. Yang, Andrew M. Saxe, Peter E. Latham

llms safety

arXiv Machine Learning

Jun 18

InTrain: Intrinsic Trainability for Zero-Cost Neural Architecture Search

arXiv:2606. 18676v1 Announce Type: new Abstract: Training-free neural architecture search promises efficient discovery of high-performance networks without costly training.

By Qinqin Zhou, Fuhai Chen, Jipeng Wu, Zhiwei Chen, Zhikai Hu, Weiwei Cai

benchmarks

arXiv Machine Learning

Jun 5

Deciphering Two Training Clocks in Grokking via Deep Linear Network Theory with Conditional ReLU Reduction

arXiv:2606. 05863v1 Announce Type: new Abstract: Grokking suggests that fitting the training data and learning a simple underlying rule may occur on different time scales.

By Hu Tan, Kuo Gai, Shihua Zhang

rag

arXiv Machine Learning

Sep 10

Capsule Lens: Locating and Tracking Concept Geometry in Model Representations

arXiv:2609.05575v1 Announce Type: new Abstract: Understanding how concepts are encoded in the internal representations of machine learning models is a central problem in mechanistic interpretability,...

By Yiming Tang, Harshvardhan Saini, Samyak Jha, Huaming Chen, Xufeng Duan, Dianbo Liu

nlp reinforcement-learning safety

arXiv Machine Learning

6d ago

Not all solutions are created equal: An analytical dissociation of functional and representational similarity in deep linear neural networks

The paper investigates the relationship between representation and function in neural networks, using analytical two‑layer linear models and simulations of nonlinear networks. It demonstrates that functional similarity and representational similarity can be dissociated: networks may share representations without sharing functions, and vice versa. The study also finds that robustness to input noise or generalization error does not constrain representations, whereas robustness to parameter noise forces networks to adopt task‑specific representations, indicating that representational alignment reflects computational advantages beyond mere functional alignment.

By Lukas Braun, Erin Grant, Andrew M. Saxe

safety

arXiv AI

Jun 30

Informational Frustration in Neural Manifolds: Shannon Bottlenecks and the Limits of Learnability

arXiv:2606. 30512v1 Announce Type: cross Abstract: Why overparameterised deep networks generalise so remarkably well remains one of the most stubborn open questions in machine learning theory.

By Srinivasa Rao P., Vangmayi P Reddy

arXiv Machine Learning

1d ago

Learning PDE solution operators with variable initial conditions via Latent Dynamics Networks

arXiv:2610.08475v1 Announce Type: new Abstract: In many-query scenarios, data-driven surrogate models provide an efficient alternative to high-fidelity solvers for simulating physical systems governe...

By Stefano Maria Pizzamiglio, Stefano Pagani, Francesco Regazzoni

diffusion

arXiv Machine Learning

Jul 9

Network Dynamics-Based Framework for Understanding Deep Neural Networks

arXiv:2501. 02436v5 Announce Type: replace Abstract: Advancements in artificial intelligence call for a deeper understanding of the fundamental mechanisms underlying deep learning.

By Yuchen Lin, Yong Zhang, Sihan Feng, Hong Zhao

fine-tuning

Related stories