:: Library Catalog

封面圖片

Saved in:

書目詳細資料
Main Authors:	Tyagi, Sahil, Wang, Feiyi
格式:	Preprint
出版:	2026
主題:	Machine Learning Artificial Intelligence
在線閱讀:	https://arxiv.org/abs/2603.18112
標簽:	添加標簽沒有標簽, 成為第一個標記此記錄!

相似書籍

On Using Large-Batches in Federated Learning
由: Tyagi, Sahil
出版: (2025)

OmniFed: A Modular Framework for Configurable Federated Learning from Edge to HPC
由: Tyagi, Sahil, et al.
出版: (2025)

Piper: Efficient Large-Scale MoE Training via Resource Modeling and Pipelined Hybrid Parallelism
由: Dash, Sajal, et al.
出版: (2026)

Revisiting LARS for Large Batch Training Generalization of Neural Networks
由: Do, Khoi, et al.
出版: (2023)

Reasoning Stabilization Point: A Training-Time Signal for Stable Evidence and Shortcut Reliance
由: Dhayalkar, Sahil Rajesh
出版: (2026)

Synergizing Large Language Models and Task-specific Models for Time Series Anomaly Detection
由: Chen, Feiyi, et al.
出版: (2025)

Towards Optimizing the Costs of LLM Usage
由: Shekhar, Shivanshu, et al.
出版: (2024)

RACE Attention: A Strictly Linear-Time Attention Layer for Training on Outrageously Large Contexts
由: Joshi, Sahil, et al.
出版: (2025)

Robust Batch-Level Query Routing for Large Language Models under Cost and Capacity Constraints
由: Markovic-Voronov, Jelena, et al.
出版: (2026)

Accelerating Large-Scale Dataset Distillation via Exploration-Exploitation Optimization
由: Alahmadi, Muhammad J., et al.
出版: (2026)

Trust the Batch, On- or Off-Policy: Adaptive Policy Optimization for RL Post-Training
由: Fakoor, Rasool, et al.
出版: (2026)

Training Greedy Policy for Proposal Batch Selection in Expensive Multi-Objective Combinatorial Optimization
由: Lee, Deokjae, et al.
出版: (2024)

GraVAC: Adaptive Compression for Communication-Efficient Distributed DL Training
由: Tyagi, Sahil, et al.
出版: (2023)

Beyond the Mean: Fisher-Orthogonal Projection for Natural Gradient Descent in Large Batch Training
由: Lu, Yishun, et al.
出版: (2025)

A Combinatorial Theory of Dropout: Subnetworks, Graph Geometry, and Generalization
由: Dhayalkar, Sahil Rajesh
出版: (2025)

Building Expressive and Tractable Probabilistic Generative Models: A Review
由: Sidheekh, Sahil, et al.
出版: (2024)

Adaptive Batch-Wise Sample Scheduling for Direct Preference Optimization
由: Huang, Zixuan, et al.
出版: (2025)

A Decomposable Forward Process in Diffusion Models for Time-Series Forecasting
由: Caldas, Francisco, et al.
出版: (2026)

Scaling Up Data Parallelism in Decentralized Deep Learning
由: Xie, Bing, et al.
出版: (2025)

Efficient GNN Training Through Structure-Aware Randomized Mini-Batching
由: Balaji, Vignesh, et al.
出版: (2025)

Time Transfer: On Optimal Learning Rate and Batch Size In The Infinite Data Limit
由: Filatov, Oleg, et al.
出版: (2024)

Batch Acquisition Function Evaluations and Decouple Optimizer Updates for Faster Bayesian Optimization
由: Irie, Kaichi, et al.
出版: (2025)

Pareto Front-Diverse Batch Multi-Objective Bayesian Optimization
由: Ahmadianshalchi, Alaleh, et al.
出版: (2024)

Edge Intelligence Optimization for Large Language Model Inference with Batching and Quantization
由: Zhang, Xinyuan, et al.
出版: (2024)

BatchLLM: Optimizing Large Batched LLM Inference with Global Prefix Sharing and Throughput-oriented Token Batching
由: Zheng, Zhen, et al.
出版: (2024)

Large-Batch, Iteration-Efficient Neural Bayesian Design Optimization
由: Ansari, Navid, et al.
出版: (2023)

Learning Multi-Pattern Normalities in the Frequency Domain for Efficient Time Series Anomaly Detection
由: Chen, Feiyi, et al.
出版: (2023)

Accelerating Distributed ML Training via Selective Synchronization
由: Tyagi, Sahil, et al.
出版: (2023)

Self-Certifying Primal-Dual Optimization Proxies for Large-Scale Batch Economic Dispatch
由: Klamkin, Michael, et al.
出版: (2025)

From Theory to Throughput: CUDA-Optimized APML for Large-Batch 3D Learning
由: Sharifipour, Sasan, et al.
出版: (2025)

Test-Time Training on Graphs with Large Language Models (LLMs)
由: Zhang, Jiaxin, et al.
出版: (2024)

Amortized Latent Steering: Low-Cost Alternative to Test-Time Optimization
由: Egbuna, Nathan, et al.
出版: (2025)

Batch Bayesian Active Learning with Partial Batch Label Sampling
由: Hu, Kangping, et al.
出版: (2025)

Federated Instrumental Variable Analysis via Federated Generalized Method of Moments
由: Geetika, et al.
出版: (2025)

Generative AI in Ship Design
由: Thakur, Sahil, et al.
出版: (2024)

Attention as Binding: A Vector-Symbolic Perspective on Transformer Reasoning
由: Dhayalkar, Sahil Rajesh
出版: (2025)

Dynamic Context Adaptation and Information Flow Control in Transformers: Introducing the Evaluator Adjuster Unit and Gated Residual Connections
由: Dhayalkar, Sahil Rajesh
出版: (2024)

Extending Test-Time Scaling: A 3D Perspective with Context, Batch, and Turn
由: Yu, Chao, et al.
出版: (2025)

Sample Transform Cost-Based Training-Free Hallucination Detector for Large Language Models
由: Ding, Zeyang, et al.
出版: (2026)

DVPO: Distributional Value Modeling-based Policy Optimization for LLM Post-Training
由: Zhu, Dingwei, et al.
出版: (2025)