Image de couverture de livre

Geometric Insights into Focal Loss: Reducing Curvature for Enhanced Model Calibration

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Kimura, Masanari, Naganuma, Hiroki
Format:	Preprint
Publié:	2024
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Heteroscedastic Double Bayesian Elastic Net
par: Kimura, Masanari
Publié: (2025)

An Empirical Study of Pre-trained Model Selection for Out-of-Distribution Generalization and Calibration
par: Naganuma, Hiroki, et autres
Publié: (2023)

Test-Time Augmentation Meets Variational Bayes
par: Kimura, Masanari, et autres
Publié: (2024)

A Short Survey on Importance Weighting for Machine Learning
par: Kimura, Masanari, et autres
Publié: (2024)

Theoretical and Practical Analysis of Fréchet Regression via Comparison Geometry
par: Kimura, Masanari, et autres
Publié: (2025)

A Mean Curvature Approach to Boundary Detection: Geometric Insights for Unsupervised Learning
par: Levada, Alexandre L. M.
Publié: (2026)

Edgeworth Expansion for Semi-hard Triplet Loss
par: Kimura, Masanari
Publié: (2025)

On permutation-invariant neural networks
par: Kimura, Masanari, et autres
Publié: (2024)

Feature-Function Curvature Analysis: A Geometric Framework for Explaining Differentiable Models
par: Najafi, Hamed, et autres
Publié: (2025)

A Unified Noise-Curvature View of Loss of Trainability
par: Baveja, Gunbir Singh, et autres
Publié: (2025)

Geometric Embedding Alignment via Curvature Matching in Transfer Learning
par: Ko, Sung Moon, et autres
Publié: (2025)

Geometric Prior-Guided Federated Prompt Calibration
par: Luo, Fei, et autres
Publié: (2025)

Explaining Black-box Model Predictions via Two-level Nested Feature Attributions with Consistency Property
par: Yoshikawa, Yuya, et autres
Publié: (2024)

Geometric Mixture-of-Experts with Curvature-Guided Adaptive Routing for Graph Representation Learning
par: Cao, Haifang, et autres
Publié: (2026)

A Multi-Modal CNN-LSTM Framework with Multi-Head Attention and Focal Loss for Real-Time Elderly Fall Detection
par: Zhou, Lijie, et autres
Publié: (2026)

Mitigating Plasticity Loss in Continual Reinforcement Learning by Reducing Churn
par: Tang, Hongyao, et autres
Publié: (2025)

CurvGAD: Leveraging Curvature for Enhanced Graph Anomaly Detection
par: Grover, Karish, et autres
Publié: (2025)

Adaptive Batch Sizes Using Non-Euclidean Gradient Noise Scales for Stochastic Sign and Spectral Descent
par: Naganuma, Hiroki, et autres
Publié: (2026)

Focal Loss based Residual Convolutional Neural Network for Speech Emotion Recognition
par: Tripathi, Suraj, et autres
Publié: (2019)

Representer Theorems for Metric and Preference Learning: Geometric Insights and Algorithms
par: Morteza, Peyman
Publié: (2023)

Hybrid Focal and Full-Range Attention Based Graph Transformers
par: Zhu, Minhong, et autres
Publié: (2023)

Harnessing Optimization Dynamics for Curvature-Informed Model Merging
par: Mahdavinia, Pouria, et autres
Publié: (2025)

Smoothed Energy Guidance: Guiding Diffusion Models with Reduced Energy Curvature of Attention
par: Hong, Susung
Publié: (2024)

Towards Understanding Variants of Invariant Risk Minimization through the Lens of Calibration
par: Yoshida, Kotaro, et autres
Publié: (2024)

Enhancing Deep Neural Network Reliability with Refinement and Calibration
par: Hebbalaguppe, Ramya, et autres
Publié: (2026)

SCPL: Enhancing Neural Network Training Throughput with Decoupled Local Losses and Model Parallelism
par: Ho, Ming-Yao, et autres
Publié: (2026)

Calibration of Continual Learning Models
par: Li, Lanpei, et autres
Publié: (2024)

Understanding Test-Time Augmentation
par: Kimura, Masanari
Publié: (2024)

Higher-Order Asymptotics of Test-Time Adaptation for Batch Normalization Statistics
par: Kimura, Masanari
Publié: (2025)

Information Geometry of Absorbing Markov-Chain and Discriminative Random Walks
par: Kimura, Masanari
Publié: (2026)

Graph-Smoothed Bayesian Black-Box Shift Estimator and Its Information Geometry
par: Kimura, Masanari
Publié: (2025)

Exploring Criteria of Loss Reweighting to Enhance LLM Unlearning
par: Yang, Puning, et autres
Publié: (2025)

Teaching Your Models to Understand Code via Focal Preference Alignment
par: Wu, Jie, et autres
Publié: (2025)

CA-HFP: Curvature-Aware Heterogeneous Federated Pruning with Model Reconstruction
par: Hu, Gang, et autres
Publié: (2026)

HELM: Hyperbolic Large Language Models via Mixture-of-Curvature Experts
par: He, Neil, et autres
Publié: (2025)

Confidence Calibration in Large Language Models
par: Michael, Noam, et autres
Publié: (2026)

RicciFlowRec: A Geometric Root Cause Recommender Using Ricci Curvature on Financial Graphs
par: Sun, Zhongtian, et autres
Publié: (2025)

Enhancing Output Diversity Improves Conjugate Gradient-based Adversarial Attacks
par: Yamamura, Keiichiro, et autres
Publié: (2024)

MemLoss: Enhancing Adversarial Training with Recycling Adversarial Examples
par: Mahdi, Soroush, et autres
Publié: (2025)

Restoring Calibration for Aligned Large Language Models: A Calibration-Aware Fine-Tuning Approach
par: Xiao, Jiancong, et autres
Publié: (2025)