Copertina

Learning to Forget with Information Divergence Reweighted Objectives for Noisy Labels

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Birrell, Jeremiah, Ebrahimi, Reza
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Optimal Transport Regularized Divergences: Application to Adversarial Robustness
di: Birrell, Jeremiah, et al.
Pubblicazione: (2023)

Statistical Error Bounds for GANs with Nonlinear Objective Functionals
di: Birrell, Jeremiah
Pubblicazione: (2024)

Concentration Inequalities for Stochastic Optimization of Unbounded Objective Functions with Application to Denoising Score Matching
di: Birrell, Jeremiah
Pubblicazione: (2025)

Statistical Guarantees for Distributionally Robust Optimization with Optimal Transport and OT-Regularized Divergences
di: Birrell, Jeremiah, et al.
Pubblicazione: (2026)

Differentially Private Stochastic Gradient Descent with Fixed-Size Minibatches: Tighter RDP Guarantees with or without Replacement
di: Birrell, Jeremiah, et al.
Pubblicazione: (2024)

Information Theoretic Adversarial Training of Large Language Models
di: Zhang, Yiwei, et al.
Pubblicazione: (2026)

Revisiting Meta-Learning with Noisy Labels: Reweighting Dynamics and Theoretical Guarantees
di: Zhang, Yiming, et al.
Pubblicazione: (2025)

An Interactive Framework for Implementing Privacy-Preserving Federated Learning: Experiments on Large Language Models
di: Ahmadi, Kasra, et al.
Pubblicazione: (2025)

DFedReweighting: A Unified Framework for Objective-Oriented Reweighting in Decentralized Federated Learning
di: Zhang, Kaichuang, et al.
Pubblicazione: (2025)

May the Forgetting Be with You: Alternate Replay for Learning with Noisy Labels
di: Millunzi, Monica, et al.
Pubblicazione: (2024)

CLID-MU: Cross-Layer Information Divergence Based Meta Update Strategy for Learning with Noisy Labels
di: Hu, Ruofan, et al.
Pubblicazione: (2025)

Demystifying Diffusion Objectives: Reweighted Losses are Better Variational Bounds
di: Shi, Jiaxin, et al.
Pubblicazione: (2025)

TapWeight: Reweighting Pretraining Objectives for Task-Adaptive Pretraining
di: Zhang, Ruiyi, et al.
Pubblicazione: (2024)

Deep Learning Classification With Noisy Labels
di: Sanchez, Guillaume, et al.
Pubblicazione: (2020)

Noisy Early Stopping for Noisy Labels
di: Toner, William, et al.
Pubblicazione: (2024)

FaLW: A Forgetting-aware Loss Reweighting for Long-tailed Unlearning
di: Yu, Liheng, et al.
Pubblicazione: (2026)

Learning Discriminative Dynamics with Label Corruption for Noisy Label Detection
di: Kim, Suyeon, et al.
Pubblicazione: (2024)

Nonlinear denoising score matching for enhanced learning of structured distributions
di: Birrell, Jeremiah, et al.
Pubblicazione: (2024)

Variational Rectification Inference for Learning with Noisy Labels
di: Sun, Haoliang, et al.
Pubblicazione: (2026)

High-dimensional Learning with Noisy Labels
di: Firdoussi, Aymane El, et al.
Pubblicazione: (2024)

Estimating Noisy Class Posterior with Part-level Labels for Noisy Label Learning
di: Zhao, Rui, et al.
Pubblicazione: (2024)

More is not always better? Enhancing Many-Shot In-Context Learning with Differentiated and Reweighting Objectives
di: Zhang, Xiaoqing, et al.
Pubblicazione: (2025)

FedNoisy: Federated Noisy Label Learning Benchmark
di: Liang, Siqi, et al.
Pubblicazione: (2023)

Learning to Clean: Reinforcement Learning for Noisy Label Correction
di: Heidari, Marzi, et al.
Pubblicazione: (2025)

TMLC-Net: Transferable Meta Label Correction for Noisy Label Learning
di: Li, Mengyang
Pubblicazione: (2025)

Efficient Bilevel Optimization for Meta Label Correction in Noisy Label Learning
di: Nguyen, Ba Hoang Anh, et al.
Pubblicazione: (2026)

Introducing Fractional Classification Loss for Robust Learning with Noisy Labels
di: Kurucu, Mert Can, et al.
Pubblicazione: (2025)

Understanding and Mitigating the Bias in Sample Selection for Learning with Noisy Labels
di: Wei, Qi, et al.
Pubblicazione: (2024)

An Empirical Study on Noisy Data and LLM Pretraining Loss Divergence
di: Zhang, Qizhen, et al.
Pubblicazione: (2026)

Nested Graph Pseudo-Label Refinement for Noisy Label Domain Adaptation Learning
di: Wang, Yingxu, et al.
Pubblicazione: (2025)

Learning Robust Reward Machines from Noisy Labels
di: Parac, Roko, et al.
Pubblicazione: (2024)

Dirichlet-Based Prediction Calibration for Learning with Noisy Labels
di: Zong, Chen-Chen, et al.
Pubblicazione: (2024)

Learning from Noisy Labels via Conditional Distributionally Robust Optimization
di: Guo, Hui, et al.
Pubblicazione: (2024)

Multiclass Learning from Noisy Labels for Non-decomposable Performance Measures
di: Zhang, Mingyuan, et al.
Pubblicazione: (2024)

EchoAlign: Bridging Generative and Discriminative Learning under Noisy Labels
di: Zheng, Yuxiang, et al.
Pubblicazione: (2024)

Robust Machine Unlearning for Quantized Neural Networks via Adaptive Gradient Reweighting with Similar Labels
di: Tong, Yujia, et al.
Pubblicazione: (2025)

Joint Asymmetric Loss for Learning with Noisy Labels
di: Wang, Jialiang, et al.
Pubblicazione: (2025)

Federated Learning with Instance-Dependent Noisy Label
di: Wang, Lei, et al.
Pubblicazione: (2023)

Foster Adaptivity and Balance in Learning with Noisy Labels
di: Sheng, Mengmeng, et al.
Pubblicazione: (2024)

The Exploration of Error Bounds in Classification with Noisy Labels
di: Liu, Haixia, et al.
Pubblicazione: (2025)