Imagen de Portada

Selective Matching Losses -- Not All Scores Are Created Equal

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Shamir, Gil I., Warmuth, Manfred K.
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

Not All LLM Reasoners Are Created Equal
por: Hosseini, Arian, et al.
Publicado: (2024)

Adversarial Samples Are Not Created Equal
por: Crawford, Jennifer, et al.
Publicado: (2026)

Online Dynamic Programming
por: Rahmanian, Holakou, et al.
Publicado: (2017)

Not All Tokens Are Created Equal: Query-Efficient Jailbreak Fuzzing for LLMs
por: Chen, Wenyu, et al.
Publicado: (2026)

Noise misleads rotation invariant algorithms on sparse targets
por: Warmuth, Manfred K., et al.
Publicado: (2024)

Not All Frequencies Are Created Equal:Towards a Dynamic Fusion of Frequencies in Time-Series Forecasting
por: Zhang, Xingyu, et al.
Publicado: (2024)

Not All Federated Learning Algorithms Are Created Equal: A Performance Evaluation Study
por: Baumgart, Gustav A., et al.
Publicado: (2024)

Optimal Transport with Tempered Exponential Measures
por: Amid, Ehsan, et al.
Publicado: (2023)

Are All Marine Species Created Equal? Performance Disparities in Underwater Object Detection
por: Wille, Melanie, et al.
Publicado: (2025)

Hard labels sampled from sparse targets mislead rotation invariant algorithms
por: Ghosh, Avrajit, et al.
Publicado: (2026)

Not All Candidates are Created Equal: A Heterogeneity-Aware Approach to Pre-ranking in Recommender Systems
por: Tong, Pengfei, et al.
Publicado: (2026)

Not All Layers Are Created Equal: Adaptive LoRA Ranks for Personalized Image Generation
por: Shenaj, Donald, et al.
Publicado: (2026)

Not All Pretraining are Created Equal: Threshold Tuning and Class Weighting for Imbalanced Polarization Tasks in Low-Resource Settings
por: Oguntade, Abass
Publicado: (2026)

Tempered Calculus for ML: Application to Hyperbolic Model Embedding
por: Nock, Richard, et al.
Publicado: (2024)

Not All Options Are Created Equal: Textual Option Weighting for Token-Efficient LLM-Based Knowledge Tracing
por: Kim, JongWoo, et al.
Publicado: (2024)

Not All Bits Are Equal: Scale-Dependent Memory Optimization Strategies for Reasoning Models
por: Kim, Junhyuck, et al.
Publicado: (2025)

All Nodes are created Not Equal: Node-Specific Layer Aggregation and Filtration for GNN
por: Wang, Shilong, et al.
Publicado: (2024)

Target Score Matching
por: De Bortoli, Valentin, et al.
Publicado: (2024)

Not All Code Is Equal: A Data-Centric Study of Code Complexity and LLM Reasoning
por: Twist, Lukas, et al.
Publicado: (2026)

Disentangling the Spectral Properties of the Hodge Laplacian: Not All Small Eigenvalues Are Equal
por: Grande, Vincent P., et al.
Publicado: (2023)

Score Matching With Missing Data
por: Givens, Josh, et al.
Publicado: (2025)

Rao-Blackwellized Score Matching on Manifolds
por: Rawal, Divit
Publicado: (2026)

Towards Healing the Blindness of Score Matching
por: Zhang, Mingtian, et al.
Publicado: (2022)

Hamiltonian Score Matching and Generative Flows
por: Holderrieth, Peter, et al.
Publicado: (2024)

Not All LLM-Generated Data Are Equal: Rethinking Data Weighting in Text Classification
por: Kuo, Hsun-Yu, et al.
Publicado: (2024)

Not All Negative Samples Are Equal: LLMs Learn Better from Plausible Reasoning
por: Di, Zixiang, et al.
Publicado: (2026)

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

Hardness of Learning Fixed Parities with Neural Networks
por: Shoshani, Itamar, et al.
Publicado: (2025)

An open dataset of neural networks for hypernetwork research
por: Kurtenbach, David, et al.
Publicado: (2025)

Limitations of SGD for Multi-Index Models Beyond Statistical Queries
por: Barzilai, Daniel, et al.
Publicado: (2026)

Control Variate Score Matching for Diffusion Models
por: Kahouli, Khaled, et al.
Publicado: (2025)

Score Matching for Estimating Finite Point Processes
por: Cao, Haoqun, et al.
Publicado: (2025)

Not All Symbols Are Equal: Importance-Aware Constellation Design for Semantic Communication
por: Shaju, Albert, et al.
Publicado: (2026)

Is Score Matching Suitable for Estimating Point Processes?
por: Cao, Haoqun, et al.
Publicado: (2024)

Simulating Diffusion Bridges with Score Matching
por: Heng, Jeremy, et al.
Publicado: (2021)

Adaptive Token-Weighted Differential Privacy for LLMs: Not All Tokens Require Equal Protection
por: Yu, Manjiang, et al.
Publicado: (2025)

Not All Forgetting Is Equal: Architecture-Dependent Retention Dynamics in Fine-Tuned Image Classifiers
por: Daga, Miit, et al.
Publicado: (2026)

Not All Denoising Steps Are Equal: Model Scheduling for Faster Masked Diffusion Language Models
por: Sedykh, Ivan, et al.
Publicado: (2026)

Not All Invariants Are Equal: Curating Training Data to Accelerate Program Verification with SLMs
por: Pinto, Ido, et al.
Publicado: (2026)

Expressive Score-Based Priors for Distribution Matching with Geometry-Preserving Regularization
por: Gong, Ziyu, et al.
Publicado: (2025)