Imagen de Portada

Rethinking Neural-based Matrix Inversion: Why can't, and Where can

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Ji, Yuliang, Wu, Jian, Xi, Yuanzhe
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

I can't see it but I can Fine-tune it: On Encrypted Fine-tuning of Transformers using Fully Homomorphic Encryption
por: Panzade, Prajwal, et al.
Publicado: (2024)

You can't handle the (dirty) truth: Data-centric insights improve pseudo-labeling
por: Seedat, Nabeel, et al.
Publicado: (2024)

Why can't Epidemiology be automated (yet)?
por: Bann, David, et al.
Publicado: (2025)

FlexAct: Why Learn when you can Pick?
por: Kumar, Ramnath, et al.
Publicado: (2026)

Influence-based Attributions can be Manipulated
por: Yadav, Chhavi, et al.
Publicado: (2024)

Why social sciences are natural, and why they can't
por: JESÚS ZAMORA-BONILLA
Publicado: (2012)

Unraveling the Rainbow: can value-based methods schedule?
por: Corrêa, Arthur, et al.
Publicado: (2025)

Optimization for Neural Operators can Benefit from Width
por: Cisneros-Velarde, Pedro, et al.
Publicado: (2025)

When, Where and Why to Average Weights?
por: Ajroldi, Niccolò, et al.
Publicado: (2025)

Incorruptible Neural Networks: Training Models that can Generalize to Large Internal Perturbations
por: Jacobson, Philip, et al.
Publicado: (2026)

Why can't we be friends? Untangling conjoined polarization in America
por: Julie M. Norman, et al.
Publicado: (2025)

Unmasking On-Policy Distillation: Where It Helps, Where It Hurts, and Why
por: Armandpour, Mohammadreza, et al.
Publicado: (2026)

Embedding-based classifiers can detect prompt injection attacks
por: Ayub, Md. Ahsan, et al.
Publicado: (2024)

Optimistic critics can empower small actors
por: Mastikhina, Olya, et al.
Publicado: (2025)

VAR: Visual Analysis for Rashomon Set of Machine Learning Models' Performance
por: Jin, Yuanzhe
Publicado: (2025)

If you can distinguish, you can express: Galois theory, Stone--Weierstrass, machine learning, and linguistics
por: Blum-Smith, Ben, et al.
Publicado: (2025)

When can we Approximate Wide Contrastive Models with Neural Tangent Kernels and Principal Component Analysis?
por: Anil, Gautham Govind, et al.
Publicado: (2024)

Why Line Search when you can Plane Search? SO-Friendly Neural Networks allow Per-Iteration Optimization of Learning and Momentum Rates for Every Layer
por: Shea, Betty, et al.
Publicado: (2024)

Convolutional Neural Networks can achieve binary bail judgement classification
por: Barman, Amit, et al.
Publicado: (2024)

Transformers can do Bayesian Clustering
por: Bhaskaran, Prajit, et al.
Publicado: (2025)

Graph Diffusion that can Insert and Delete
por: Ninniri, Matteo, et al.
Publicado: (2025)

Post-Norm can Resharpen Attention
por: Zsámboki, Pál, et al.
Publicado: (2025)

Text embedding models can be great data engineers
por: Kazemian, Iman, et al.
Publicado: (2025)

Clustering with minimum spanning trees: How good can it be?
por: Gagolewski, Marek, et al.
Publicado: (2023)

HiGP: A high-performance Python package for Gaussian Process
por: Huang, Hua, et al.
Publicado: (2025)

Rethinking Non-Negative Matrix Factorization with Implicit Neural Representations
por: Subramani, Krishna, et al.
Publicado: (2024)

Differential Subgroup Discovery: Characterizing Where Two Populations Differ, and Why
por: Xu, Sascha, et al.
Publicado: (2026)

Scaling can lead to compositional generalization
por: Redhardt, Florian, et al.
Publicado: (2025)

How can representation dimension dominate structurally pruned LLMs?
por: Xu, Mingxue, et al.
Publicado: (2025)

Graph Neural Networks can Recover the Hidden Features Solely from the Graph Structure
por: Sato, Ryoma
Publicado: (2023)

Smoothed Online Classification can be Harder than Batch Classification
por: Raman, Vinod, et al.
Publicado: (2024)

Learning Regularizers: Learning Optimizers that can Regularize
por: Sahoo, Suraj Kumar, et al.
Publicado: (2025)

Sublinear iterations can suffice even for DDPMs
por: Zhang, Matthew S., et al.
Publicado: (2025)

Posterior Covariance Structures in Gaussian Processes
por: Cai, Difeng, et al.
Publicado: (2024)

Neural networks can detect model-free static arbitrage strategies
por: Neufeld, Ariel, et al.
Publicado: (2023)

You can't rely on fireman forensics
por: Mejía, Robin
Publicado: (2005)

Learning Pareto manifolds in high dimensions: How can regularization help?
por: Wegel, Tobias, et al.
Publicado: (2025)

Transformers know more than they can tell -- Learning the Collatz sequence
por: Charton, François, et al.
Publicado: (2025)

When can transformers compositionally generalize in-context?
por: Kobayashi, Seijin, et al.
Publicado: (2024)

Network Inversion of Binarised Neural Nets
por: Suhail, Pirzada, et al.
Publicado: (2024)