Copertina

Provable Benefit of Sign Descent: A Minimal Model Under Heavy-Tailed Class Imbalance

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Yadav, Robin, Xie, Shuo, Wang, Tianhao, Li, Zhiyuan
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Heavy-Tailed Class Imbalance and Why Adam Outperforms Gradient Descent on Language Models
di: Kunstner, Frederik, et al.
Pubblicazione: (2024)

Adaptive Heavy-Tailed Stochastic Gradient Descent
di: Gong, Bodu, et al.
Pubblicazione: (2025)

$(ε, u)$-Adaptive Regret Minimization in Heavy-Tailed Bandits
di: Genalti, Gianmarco, et al.
Pubblicazione: (2023)

Heavy-Tailed Class-Conditional Priors for Long-Tailed Generative Modeling
di: Bouayed, Aymene Mohammed, et al.
Pubblicazione: (2025)

Provable Benefits of In-Tool Learning for Large Language Models
di: Houliston, Sam, et al.
Pubblicazione: (2025)

Federated Active Learning Under Extreme Non-IID and Global Class Imbalance
di: Zong, Chen-Chen, et al.
Pubblicazione: (2026)

A Hierarchical Language Model with Predictable Scaling Laws and Provable Benefits of Reasoning
di: Gaitonde, Jason, et al.
Pubblicazione: (2026)

Provable Long-Range Benefits of Next-Token Prediction
di: Cao, Xinyuan, et al.
Pubblicazione: (2025)

Provable Benefit of Cutout and CutMix for Feature Learning
di: Oh, Junsoo, et al.
Pubblicazione: (2024)

Provable Acceleration for Diffusion Models under Minimal Assumptions
di: Li, Gen, et al.
Pubblicazione: (2024)

Class-Imbalanced Graph Learning without Class Rebalancing
di: Liu, Zhining, et al.
Pubblicazione: (2023)

A Tale of Two Geometries: Adaptive Optimizers and Non-Euclidean Descent
di: Xie, Shuo, et al.
Pubblicazione: (2025)

TailedTS: Benchmark Dataset for Heavy-Tailed Time Series Prediction and Periodicity Quantification
di: Chen, Xinyu, et al.
Pubblicazione: (2026)

Kolmogorov Arnold Networks (KANs) for Imbalanced Data -- An Empirical Perspective
di: Yadav, Pankaj, et al.
Pubblicazione: (2025)

ONG: Orthogonal Natural Gradient Descent
di: Yadav, Yajat, et al.
Pubblicazione: (2025)

Robust Offline Reinforcement learning with Heavy-Tailed Rewards
di: Zhu, Jin, et al.
Pubblicazione: (2023)

Markov Chain Decoders Overcome the Heavy-Tail Limitations of Lipschitz Generative Models
di: Ziani, Abdelhakim, et al.
Pubblicazione: (2026)

Metastable Dynamics of Chain-of-Thought Reasoning: Provable Benefits of Search, RL and Distillation
di: Kim, Juno, et al.
Pubblicazione: (2025)

Beyond Rebalancing: Benchmarking Binary Classifiers Under Class Imbalance Without Rebalancing Techniques
di: Nawaz, Ali, et al.
Pubblicazione: (2025)

Time-Series Contrastive Learning against False Negatives and Class Imbalance
di: Jin, Xiyuan, et al.
Pubblicazione: (2023)

Interpretable Models Capable of Handling Systematic Missingness in Imbalanced Classes and Heterogeneous Datasets
di: Ghosh, Sreejita, et al.
Pubblicazione: (2022)

Multimodal Deep Generative Model for Semi-Supervised Learning under Class Imbalance
di: Yoon, Heegeon, et al.
Pubblicazione: (2026)

Provable Benefits of Complex Parameterizations for Structured State Space Models
di: Ran-Milo, Yuval, et al.
Pubblicazione: (2024)

HTMuon: Improving Muon via Heavy-Tailed Spectral Correction
di: Pang, Tianyu, et al.
Pubblicazione: (2026)

Resilient Class-Incremental Learning: on the Interplay of Drifting, Unlabelled and Imbalanced Data Streams
di: Li, Jin, et al.
Pubblicazione: (2026)

Provable Failure of Language Models in Learning Majority Boolean Logic via Gradient Descent
di: Chen, Bo, et al.
Pubblicazione: (2025)

A Cost-Sensitive Transformer Model for Prognostics Under Highly Imbalanced Industrial Data
di: Beikmohammadi, Ali, et al.
Pubblicazione: (2024)

BuffGraph: Enhancing Class-Imbalanced Node Classification via Buffer Nodes
di: Wang, Qian, et al.
Pubblicazione: (2024)

Towards Collaborative Fairness in Federated Learning Under Imbalanced Covariate Shift
di: Yu, Tianrun, et al.
Pubblicazione: (2025)

Temporal Imbalance of Positive and Negative Supervision in Class-Incremental Learning
di: Ma, Jinge, et al.
Pubblicazione: (2026)

When Noisy Labels Meet Class Imbalance on Graphs: A Graph Augmentation Method with LLM and Pseudo Label
di: Xia, Riting, et al.
Pubblicazione: (2025)

Rebalancing the Scales: A Systematic Mapping Study of Generative Adversarial Networks (GANs) in Addressing Data Imbalance
di: Yadav, Pankaj, et al.
Pubblicazione: (2025)

Synthetic Tabular Data Generation for Class Imbalance and Fairness: A Comparative Study
di: Panagiotou, Emmanouil, et al.
Pubblicazione: (2024)

Towards Understanding The Calibration Benefits of Sharpness-Aware Minimization
di: Tan, Chengli, et al.
Pubblicazione: (2025)

Class-Imbalanced-Aware Adaptive Dataset Distillation for Scalable Pretrained Model on Credit Scoring
di: Li, Xia, et al.
Pubblicazione: (2025)

One LR Doesn't Fit All: Heavy-Tail Guided Layerwise Learning Rates for LLMs
di: He, Di, et al.
Pubblicazione: (2026)

LLM-Empowered Class Imbalanced Graph Prompt Learning for Online Drug Trafficking Detection
di: Ma, Tianyi, et al.
Pubblicazione: (2025)

Data-Free Generative Replay for Class-Incremental Learning on Imbalanced Data
di: Younis, Sohaib, et al.
Pubblicazione: (2024)

VIGraph: Generative Self-supervised Learning for Class-Imbalanced Node Classification
di: Hu, Yulan, et al.
Pubblicazione: (2023)

DAMEL: Dual-Axis Multi-Expert Learning for Class-Imbalanced Learning
di: Lee, Hyuck, et al.
Pubblicazione: (2026)