Imagen de Portada

Guiding Neural Collapse: Optimising Towards the Nearest Simplex Equiangular Tight Frame

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Markou, Evan, Ajanthan, Thalaiyasingam, Gould, Stephen
Formato:	Preprint
Publicado:	2024
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Sharper Convergence Rates for Nonconvex Optimisation via Reduction Mappings
por: Markou, Evan, et al.
Publicado: (2025)

Self-Supervision Improves Diffusion Models for Tabular Data Imputation
por: Liu, Yixin, et al.
Publicado: (2024)

Protocol Models: Scaling Decentralized Training with Communication-Efficient Model Parallelism
por: Ramasinghe, Sameera, et al.
Publicado: (2025)

Nesterov Method for Asynchronous Pipeline Parallel Optimization
por: Ajanthan, Thalaiyasingam, et al.
Publicado: (2025)

Scaling Prompt Instructed Zero Shot Composed Image Retrieval with Image-Only Data
por: Duan, Yiqun, et al.
Publicado: (2025)

Towards Scalable Backpropagation-Free Gradient Estimation
por: Wang, Daniel, et al.
Publicado: (2025)

Leveraging Intermediate Neural Collapse with Simplex ETFs for Efficient Deep Neural Networks
por: Liu, Emily
Publicado: (2024)

$k$-Homogeneous Equiangular Tight Frames
por: King, Emily J.
Publicado: (2025)

Pushing Toward the Simplex Vertices: A Simple Remedy for Code Collapse in Smoothed Vector Quantization
por: Morita, Takashi
Publicado: (2025)

A Simplex Witness Certificate for Constant Collapse in Variational Autoencoders
por: Zhang, Zegu, et al.
Publicado: (2026)

AsyncMesh: Fully Asynchronous Optimization for Data and Pipeline Parallelism
por: Ajanthan, Thalaiyasingam, et al.
Publicado: (2026)

NuMuon: Nuclear-Norm-Constrained Muon for Compressible LLM Training
por: Dolatabadi, Hadi Mohaghegh, et al.
Publicado: (2026)

Towards Continual Learning Desiderata via HSIC-Bottleneck Orthogonalization and Equiangular Embedding
por: Li, Depeng, et al.
Publicado: (2024)

SENTINEL: Stagewise Integrity Verification for Pipeline Parallel Decentralized Training
por: Dolatabadi, Hadi Mohaghegh, et al.
Publicado: (2026)

Nearest Neighbour with Bandit Feedback
por: Pasteris, Stephen, et al.
Publicado: (2023)

On the Robustness of Neural Collapse and the Neural Collapse of Robustness
por: Su, Jingtong, et al.
Publicado: (2023)

Decoding as Optimisation on the Probability Simplex: From Top-K to Top-P (Nucleus) to Best-of-K Samplers
por: Ji, Xiaotong, et al.
Publicado: (2026)

Label Distribution Learning using the Squared Neural Family on the Probability Simplex
por: Zhang, Daokun, et al.
Publicado: (2024)

Towards Understanding Neural Collapse: The Effects of Batch Normalization and Weight Decay
por: Pan, Leyan, et al.
Publicado: (2023)

Path Integral Optimiser: Global Optimisation via Neural Schrödinger-Föllmer Diffusion
por: McGuinness, Max, et al.
Publicado: (2025)

Mixture of Experts with Soft Nearest Neighbor Loss: Resolving Expert Collapse via Representation Disentanglement
por: Agarap, Abien Fred, et al.
Publicado: (2026)

Better Neural Network Expressivity: Subdividing the Simplex
por: Bakaev, Egor, et al.
Publicado: (2025)

Simplex Deep Linear Discriminant Analysis
por: Tezekbayev, Maxat, et al.
Publicado: (2026)

Beyond Distribution Estimation: Simplex Anchored Structural Inference Towards Universal Semi-Supervised Learning
por: Hou, Yaxin, et al.
Publicado: (2026)

Simplex-to-Euclidean Bijections for Categorical Flow Matching
por: Williams, Bernardo, et al.
Publicado: (2025)

Neural Collapse versus Low-rank Bias: Is Deep Neural Collapse Really Optimal?
por: Súkeník, Peter, et al.
Publicado: (2024)

Pushing Boundaries: Mixup's Influence on Neural Collapse
por: Fisher, Quinn, et al.
Publicado: (2024)

Rethinking Continual Learning with Progressive Neural Collapse
por: Wang, Zheng, et al.
Publicado: (2025)

Optimizer choice matters for the emergence of Neural Collapse
por: Zhao, Jim, et al.
Publicado: (2026)

Trojan Cleansing with Neural Collapse
por: Gu, Xihe, et al.
Publicado: (2024)

The Prevalence of Neural Collapse in Neural Multivariate Regression
por: Andriopoulos, George, et al.
Publicado: (2024)

Robust Multi-Manifold Clustering via Simplex Paths
por: Chen, Haoyu, et al.
Publicado: (2025)

Information Theoretic Bayesian Optimization over the Probability Simplex
por: Pavesi, Federico, et al.
Publicado: (2026)

The Multiclass Score-Oriented Loss (MultiSOL) on the Simplex
por: Marchetti, Francesco, et al.
Publicado: (2025)

K Nearest Neighbor-Guided Trajectory Similarity Learning
por: Chang, Yanchuan, et al.
Publicado: (2025)

Translation Equivariant Transformer Neural Processes
por: Ashman, Matthew, et al.
Publicado: (2024)

Dual Simplex Volume Maximization for Simplex-Structured Matrix Factorization
por: Abdolali, Maryam, et al.
Publicado: (2024)

The Hitchhiker's Guide to Efficient, End-to-End, and Tight DP Auditing
por: Annamalai, Meenatchi Sundaram Muthu Selva, et al.
Publicado: (2025)

Neural Algorithmic Reasoning for Combinatorial Optimisation
por: Georgiev, Dobrik, et al.
Publicado: (2023)

Nearest Neighbour Equilibrium Clustering
por: Hofmeyr, David P.
Publicado: (2025)