Cover Image

Should We Always Train Models on Fine-Grained Classes?

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Pirovano, Davide, Milanesio, Federico, Caselle, Michele, Fariselli, Piero, Osella, Matteo
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Ranking nodes in bipartite systems with a non-linear iterative map
by: Mazzolini, Andrea, et al.
Published: (2024)

Cartan Networks: Group theoretical Hyperbolic Deep Learning
by: Milanesio, Federico, et al.
Published: (2025)

Navigation through Non-Compact Symmetric Spaces: a mathematical perspective on Cartan Neural Networks
by: Fré, Pietro Giuseppe, et al.
Published: (2025)

Neural Diffusion Processes for Physically Interpretable Survival Prediction
by: Cristofoletto, Alessio, et al.
Published: (2025)

LLMs Will Always Hallucinate, and We Need to Live With This
by: Banerjee, Sourav, et al.
Published: (2024)

Beyond Cox Models: Assessing the Performance of Machine-Learning Methods in Non-Proportional Hazards and Non-Linear Survival Analysis
by: Rossi, Ivan, et al.
Published: (2025)

Tessellation Groups, Harmonic Analysis on Non-compact Symmetric Spaces and the Heat Kernel in view of Cartan Convolutional Neural Networks
by: Fré, Pietro, et al.
Published: (2025)

Should We Simultaneously Calibrate Multiple Computer Models?
by: Eweis-Labolle, Jonathan Tammer, et al.
Published: (2025)

SurvHive: a package to consistently access multiple survival-analysis packages
by: Birolo, Giovanni, et al.
Published: (2025)

Studying Effective String Theory using deep generative models
by: Caselle, Michele, et al.
Published: (2025)

Stochastic normalizing flows for Effective String Theory
by: Caselle, Michele, et al.
Published: (2024)

Sampling the lattice Nambu-Goto string using Continuous Normalizing Flows
by: Caselle, Michele, et al.
Published: (2023)

Numerical determination of the width and shape of the effective string using Stochastic Normalizing Flows
by: Caselle, Michele, et al.
Published: (2024)

Optimizers Qualitatively Alter Solutions And We Should Leverage This
by: Pascanu, Razvan, et al.
Published: (2025)

Mass Balance Approximation of Unfolding Improves Potential-Like Methods for Protein Stability Predictions
by: Rossi, Ivan, et al.
Published: (2025)

When Should We Introduce Safety Interventions During Pretraining?
by: Sam, Dylan, et al.
Published: (2026)

Always-Sparse Training by Growing Connections with Guided Stochastic Exploration
by: Heddes, Mike, et al.
Published: (2024)

Inversion dynamics of class manifolds in deep learning reveals tradeoffs underlying generalisation
by: Ciceri, Simone, et al.
Published: (2023)

Multi-Class Quantum Convolutional Neural Networks
by: Mordacci, Marco, et al.
Published: (2024)

How Should We Represent History in Interpretable Models of Clinical Policies?
by: Matsson, Anton, et al.
Published: (2024)

We Should Chart an Atlas of All the World's Models
by: Horwitz, Eliahu, et al.
Published: (2025)

When Should We Orchestrate Multiple Agents?
by: Bhatt, Umang, et al.
Published: (2025)

When Should an AI Workflow Release? Always-Valid Inference for Black-Box Generate-Verify Systems
by: Cho, Young Hyun, et al.
Published: (2026)

Sparsity is All You Need: Rethinking Biological Pathway-Informed Approaches in Deep Learning
by: Caranzano, Isabella, et al.
Published: (2025)

How Should We Meta-Learn Reinforcement Learning Algorithms?
by: Goldie, Alexander David, et al.
Published: (2025)

Zero-Shot Hierarchical Classification on the Common Procurement Vocabulary Taxonomy
by: Moiraghi, Federico, et al.
Published: (2024)

Linear Convergence of Black-Box Variational Inference: Should We Stick the Landing?
by: Kim, Kyurae, et al.
Published: (2023)

Should We Ever Prefer Decision Transformer for Offline Reinforcement Learning?
by: Omori, Yumi, et al.
Published: (2025)

Do We Always Need the Simplicity Bias? Looking for Optimal Inductive Biases in the Wild
by: Teney, Damien, et al.
Published: (2025)

Position: Federated Foundation Language Model Post-Training Should Focus on Open-Source Models
by: Agrawal, Nikita, et al.
Published: (2025)

Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data
by: Tajwar, Fahim, et al.
Published: (2024)

Always Tell Me The Odds: Fine-grained Conditional Probability Estimation
by: Wang, Liaoyaqi, et al.
Published: (2025)

For How Long Should We Be Punching? Learning Action Duration in Fighting Games
by: Nguyen, Hoang Hai, et al.
Published: (2026)

Exploiting Fine-Grained Prototype Distribution for Boosting Unsupervised Class Incremental Learning
by: Liu, Jiaming, et al.
Published: (2024)

Perplexity Cannot Always Tell Right from Wrong
by: Veličković, Petar, et al.
Published: (2026)

Fine-Grained Model Merging via Modular Expert Recombination
by: Qiu, Haiyun, et al.
Published: (2026)

JanusDDG: A Thermodynamics-Compliant Model for Sequence-Based Protein Stability via Two-Fronts Multi-Head Attention
by: Barducci, Guido, et al.
Published: (2025)

The Fine-Grained Complexity of Gradient Computation for Training Large Language Models
by: Alman, Josh, et al.
Published: (2024)

AALF: Almost Always Linear Forecasting
by: Jakobs, Matthias, et al.
Published: (2024)

TaxaDiffusion: Progressively Trained Diffusion Model for Fine-Grained Species Generation
by: Monsefi, Amin Karimi, et al.
Published: (2025)