Cover Image

A simple connection from loss flatness to compressed neural representations

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chen, Shirui, Recanatesi, Stefano, Shea-Brown, Eric
Format:	Preprint
Published:	2023
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Learning to Embed Distributions via Maximum Kernel Entropy
by: Kachaiev, Oleksii, et al.
Published: (2024)

Linearity-based neural network compression
by: Dobler, Silas, et al.
Published: (2025)

LayerCollapse: Adaptive compression of neural networks
by: Shabgahi, Soheil Zibakhsh, et al.
Published: (2023)

Variational autoencoder-based neural network model compression
by: Cheng, Liang, et al.
Published: (2024)

Addressing divergent representations from causal interventions on neural networks
by: Grant, Satchel, et al.
Published: (2025)

Elimination-compensation pruning for fully-connected neural networks
by: Ballini, Enrico, et al.
Published: (2026)

Why are hyperbolic neural networks effective? A study on hierarchical representation capability
by: Tan, Shicheng, et al.
Published: (2024)

Distill n' Explain: explaining graph neural networks using simple surrogates
by: Pereira, Tamara, et al.
Published: (2023)

KPFlow: An Operator Perspective on Dynamic Collapse Under Gradient Descent Training of Recurrent Networks
by: Hazelden, James, et al.
Published: (2025)

Perturbation: A simple and efficient adversarial tracer for representation learning in language models
by: Rozner, Joshua, et al.
Published: (2026)

Advanced atom-level representations for protein flexibility prediction utilizing graph neural networks
by: Sarparast, Sina, et al.
Published: (2024)

Tensorization is a powerful but underexplored tool for compression and interpretability of neural networks
by: Hamreras, Safa, et al.
Published: (2025)

dUltra: Ultra-Fast Diffusion Language Models via Reinforcement Learning
by: Chen, Shirui, et al.
Published: (2025)

Implicit neural representations as a coordinate-based framework for continuous environmental field reconstruction from sparse ecological observations
by: Pregowska, Agnieszka, et al.
Published: (2026)

Task complexity shapes internal representations and robustness in neural networks
by: Jankowski, Robert, et al.
Published: (2025)

FreeGAD: A Training-Free yet Effective Approach for Graph Anomaly Detection
by: Zhao, Yunfeng, et al.
Published: (2025)

LeapTS: Rethinking Time Series Forecasting as Adaptive Multi-Horizon Scheduling
by: Pan, Sheng, et al.
Published: (2026)

Noise-Resilient Unsupervised Graph Representation Learning via Multi-Hop Feature Quality Estimation
by: Li, Shiyuan, et al.
Published: (2024)

Discrete, compositional, and symbolic representations through attractor dynamics
by: Nam, Andrew, et al.
Published: (2023)

Implicit neural representation of textures
by: Kwok, Albert, et al.
Published: (2026)

Decision-focused Graph Neural Networks for Combinatorial Optimization
by: Liu, Yang, et al.
Published: (2024)

Evaluating alignment between humans and neural network representations in image-based learning tasks
by: Demircan, Can, et al.
Published: (2023)

SE3Set: Harnessing equivariant hypergraph neural networks for molecular representation learning
by: Wu, Hongfei, et al.
Published: (2024)

Deep Learning for Time Series Anomaly Detection: A Survey
by: Darban, Zahra Zamanzadeh, et al.
Published: (2022)

Knowledge-aware contrastive heterogeneous molecular graph learning
by: Chen, Mukun, et al.
Published: (2025)

Graph Sparsification via Mixture of Graphs
by: Zhang, Guibin, et al.
Published: (2024)

Outlier-robust neural network training: variation regularization meets trimmed loss to prevent functional breakdown
by: Okuno, Akifumi, et al.
Published: (2023)

On the transferability of Sparse Autoencoders for interpreting compressed models
by: Gupte, Suchit, et al.
Published: (2025)

Making deep neural networks right for the right scientific reasons by interacting with their explanations
by: Schramowski, Patrick, et al.
Published: (2020)

Artificial Agency Program: Curiosity, compression, and communication in agents
by: Csaky, Richard
Published: (2026)

Accuracy of TextFooler black box adversarial attacks on 01 loss sign activation neural network ensemble
by: Xue, Yunzhe, et al.
Published: (2024)

JaxUED: A simple and useable UED library in Jax
by: Coward, Samuel, et al.
Published: (2024)

Human alignment of neural network representations
by: Muttenthaler, Lukas, et al.
Published: (2022)

Trustworthy Graph Neural Networks: Aspects, Methods and Trends
by: Zhang, He, et al.
Published: (2022)

INSPIRE-GNN: Intelligent Sensor Placement to Improve Sparse Bicycling Network Prediction via Reinforcement Learning Boosted Graph Neural Networks
by: Gupta, Mohit, et al.
Published: (2025)

Beyond the Aggregation Dilemma: Prior-Retaining Decoupled Learning for Multimodal Graphs
by: Yan, Hao, et al.
Published: (2026)

Light-weight probing of unsupervised representations for Reinforcement Learning
by: Zhang, Wancong, et al.
Published: (2022)

Randomness and signal propagation in physics-informed neural networks (PINNs): A neural PDE perspective
by: Tucny, Jean-Michel, et al.
Published: (2025)

ST-TGExplainer: Disentangling Stability and Transition Patterns for Temporal GNN Interpretability
by: Chen, Hongjiang, et al.
Published: (2026)

FedPFT: Federated Proxy Fine-Tuning of Foundation Models
by: Peng, Zhaopeng, et al.
Published: (2024)