Feed m Birds with One Scone: Accelerating Multi-task Gradient Balancing via Bi-level Optimization

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Chen, Xuxing, He, Yun, Xu, Jiayi, Huang, Minhui, Liu, Xiaoyi, Liu, Boyang, Tian, Fei, Wei, Xiaohan, Jin, Rong, Park, Sem, Long, Bo, Feng, Xue
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning Optimization and Control
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

MultiBalance: Multi-Objective Gradient Balancing in Industrial-Scale Multi-Task Recommendation System
di: He, Yun, et al.
Pubblicazione: (2024)

Feed Two Birds with One Scone: Exploiting Wild Data for Both Out-of-Distribution Generalization and Detection
di: Bai, Haoyue, et al.
Pubblicazione: (2023)

Feed Two Birds with One Scone: Exploiting Function-Space Regularization for Both OOD Robustness and ID Fine-Tuning Performance
di: Yuan, Xiang, et al.
Pubblicazione: (2025)

Beyond Self-Consistency: Loss-Balanced Perturbation-Based Regularization Improves Industrial-Scale Ads Ranking
di: Ramazanli, Ilqar, et al.
Pubblicazione: (2025)

Accelerating Resonant Spectroscopy Simulations Using Multi-Shifted Bi-Conjugate Gradient
di: Sharma, Prakash, et al.
Pubblicazione: (2025)

Conflict-Averse Gradient Descent for Multi-task Learning
di: Liu, Bo, et al.
Pubblicazione: (2021)

Scone: Bridging Composition and Distinction in Subject-Driven Image Generation via Unified Understanding-Generation Modeling
di: Wang, Yuran, et al.
Pubblicazione: (2025)

You Cannot Feed Two Birds with One Score: the Accuracy-Naturalness Tradeoff in Translation
di: Flamich, Gergely, et al.
Pubblicazione: (2025)

The Fall of the Bibliographic Wall: Libraries and Archives in Unified Germany.
di: Sutter, Sem C.
Pubblicazione: (1994)

Fundamentos de Derecho Procesal Penal. Nieva Fenoll, Jordi, Editorial B de F, Buenos Aires, 2012. 336 pp.
di: Sem Sandoval Reyes
Pubblicazione: (2012)

El derecho probatorio a la deriva Damaška, Mirjan R. (2015): traducción Joan Picó i Junoy, (Madrid, Editorial Marcial Pons), 158 pp.
di: Sem Sandoval Reyes
Pubblicazione: (2016)

Catch-Only-One: Non-Transferable Examples for Model-Specific Authorization
di: Wang, Zihan, et al.
Pubblicazione: (2025)

Construction of Multistep Charge Transfer Pathways in Bi 0 @Bi 3+ ‐KNbO 3 for Significantly Accelerated Photoconversion of Waste Plastics
di: Xulong Fan, et al.
Pubblicazione: (2025)

Construction of Multistep Charge Transfer Pathways in Bi 0 @Bi 3+ ‐KNbO 3 for Significantly Accelerated Photoconversion of Waste Plastics
di: Xulong Fan, et al.
Pubblicazione: (2025)

UniRetriever: Multi-task Candidates Selection for Various Context-Adaptive Conversational Retrieval
di: Wang, Hongru, et al.
Pubblicazione: (2024)

Momentum-Accelerated Richardson(m) and Their Multilevel Neural Solvers
di: Wang, Zhen, et al.
Pubblicazione: (2024)

Feeding Two Birds or Favoring One? Adequacy-Fluency Tradeoffs in Evaluation and Meta-Evaluation of Machine Translation
di: Shayegh, Behzad, et al.
Pubblicazione: (2025)

A Gradient Guided Diffusion Framework for Chance Constrained Programming
di: Zhang, Boyang, et al.
Pubblicazione: (2025)

FedBCD:Communication-Efficient Accelerated Block Coordinate Gradient Descent for Federated Learning
di: Liu, Junkang, et al.
Pubblicazione: (2026)

Learning Continuous Wasserstein Barycenter Space for Generalized All-in-One Image Restoration
di: Tang, Xiaole, et al.
Pubblicazione: (2026)

ChatGPTest: opportunities and cautionary tales of utilizing AI for questionnaire pretesting
di: Olivos, Francisco, et al.
Pubblicazione: (2024)

Accelerating Diffusion Models for Inverse Problems through Shortcut Sampling
di: Liu, Gongye, et al.
Pubblicazione: (2023)

SPAR: Personalized Content-Based Recommendation via Long Engagement Attention
di: Zhang, Chiyu, et al.
Pubblicazione: (2024)

In‐Built Reactive Polymer as Versatile Electrolyte to Shield the Bi‐Electrode Surfaces for Practical Li‐Metal Batteries
di: Yaru Liu, et al.
Pubblicazione: (2026)

Male and Female Parent Birds Enhance Their Reproductive Success Using Different Strategies but the Same Optimal Pathway
di: Ning‐Ning Sun, et al.
Pubblicazione: (2025)

Collagen mRNA‐LNP Accelerates Skin Wound Healing
di: Can Li, et al.
Pubblicazione: (2025)

One Polyp Identifies All: One-Shot Polyp Segmentation with SAM via Cascaded Priors and Iterative Prompt Evolution
di: Mao, Xinyu, et al.
Pubblicazione: (2025)

Balanced assignments of periodic tasks
di: Gachet, Héloïse, et al.
Pubblicazione: (2024)

EmbSum: Leveraging the Summarization Capabilities of Large Language Models for Content-Based Recommendations
di: Zhang, Chiyu, et al.
Pubblicazione: (2024)

BiTA: Bi-Directional Tuning for Lossless Acceleration in Large Language Models
di: Lin, Feng, et al.
Pubblicazione: (2024)

Design and Implementation of Data Acquisition and Analysis System for Programming Debugging Process Based On VS Code Plug-In
di: Liu, Boyang
Pubblicazione: (2025)

BEV-GS: Feed-forward Gaussian Splatting in Bird's-Eye-View for Road Reconstruction
di: Wu, Wenhua, et al.
Pubblicazione: (2025)

Kill Two Birds with One Stone: Dual‐Metal MOF‐Nanozyme‐Decorated Hydrogels with ROS‐Scavenging, Oxygen‐Generating, and Antibacterial Abilities for Accelerating Infected Diabetic Wound Healing
di: Yun‐Jie Wei, et al.
Pubblicazione: (2024)

Multi-task Just Recognizable Difference for Video Coding for Machines: Database, Model, and Coding Application
di: Liu, Junqi, et al.
Pubblicazione: (2026)

Wheelchair Maneuvering with a Single-Spherical-Wheeled Balancing Mobile Manipulator
di: Dai, Cunxi, et al.
Pubblicazione: (2024)

Stochastic Smoothed Gradient Descent Ascent for Federated Minimax Optimization
di: Shen, Wei, et al.
Pubblicazione: (2023)

Adaptive Change Point Inference for High Dimensional Time Series with Temporal Dependence
di: Wang, Xiaoyi, et al.
Pubblicazione: (2025)

Adaptive Accelerated Gradient Descent Methods for Convex Optimization
di: Xu, Zeyi, et al.
Pubblicazione: (2026)

Unifying Generative and Dense Retrieval for Sequential Recommendation
di: Yang, Liu, et al.
Pubblicazione: (2024)

APOLLO: SGD-like Memory, AdamW-level Performance
di: Zhu, Hanqing, et al.
Pubblicazione: (2024)