Imagen de Portada

Toward Efficient Influence Function: Dropout as a Compression Tool

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhang, Yuchen, Amiri, Mohammad Mohammadi
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Optimal Singular Damage: Efficient LLM Inference in Low Storage Regimes
por: Alipour, Mohammadsajad, et al.
Publicado: (2025)

Towards Reversible Model Merging For Low-rank Weights
por: Alipour, Mohammadsajad, et al.
Publicado: (2025)

Disentangled Structural and Featural Representation for Task-Agnostic Graph Valuation
por: Falahati, Ali, et al.
Publicado: (2024)

The Alignment Game: A Theory of Long-Horizon Alignment Through Recursive Curation
por: Falahati, Ali, et al.
Publicado: (2025)

Curated Synthetic Data Doesn't Have to Collapse: A Theoretical Study of Generative Retraining with Pluralistic Preferences
por: Falahati, Ali, et al.
Publicado: (2026)

SentenceKV: Efficient LLM Inference via Sentence-Level Semantic KV Caching
por: Zhu, Yuxuan, et al.
Publicado: (2025)

OjaKV: Context-Aware Online Low-Rank KV Cache Compression
por: Zhu, Yuxuan, et al.
Publicado: (2025)

OFMU: Optimization-Driven Framework for Machine Unlearning
por: Asif, Sadia, et al.
Publicado: (2025)

Tool Unlearning for Tool-Augmented LLMs
por: Cheng, Jiali, et al.
Publicado: (2025)

A Median Perspective on Unlabeled Data for Out-of-Distribution Detection
por: Abbas, Momin, et al.
Publicado: (2025)

RefusalGuard: Geometry-Preserving Fine-Tuning for Safety in LLMs
por: Asif, Sadia, et al.
Publicado: (2026)

ZoomR: Memory Efficient Reasoning through Multi-Granularity Key Value Retrieval
por: Yang, David H., et al.
Publicado: (2026)

DeltaDQ: Ultra-High Delta Compression for Fine-Tuned LLMs via Group-wise Dropout and Separate Quantization
por: Jiang, Yanfeng, et al.
Publicado: (2024)

Training-Free Geospatial Place Representation Learning from Large-Scale Point-of-Interest Graph Data
por: Hashemi, Mohammad, et al.
Publicado: (2025)

Power to the Clients: Federated Learning in a Dictatorship Setting
por: Alipour, Mohammadsajad, et al.
Publicado: (2025)

Localising Dropout Variance in Twin Networks
por: Doyle, Cooper
Publicado: (2025)

Scalable, Explainable and Provably Robust Anomaly Detection with One-Step Flow Matching
por: Li, Zhong, et al.
Publicado: (2025)

Towards Efficient Mixture of Experts: A Holistic Study of Compression Techniques
por: He, Shwai, et al.
Publicado: (2024)

LoRA Dropout as a Sparsity Regularizer for Overfitting Control
por: Lin, Yang, et al.
Publicado: (2024)

DynamicGate MLP Conditional Computation via Learned Structural Dropout and Input Dependent Gating for Functional Plasticity
por: Choi, Yong Il
Publicado: (2026)

Leveraging GPT-4o Efficiency for Detecting Rework Anomaly in Business Processes
por: Derakhshan, Mohammad, et al.
Publicado: (2025)

An explainable approach to detect case law on housing and eviction issues within the HUDOC database
por: Mohammadi, Mohammad, et al.
Publicado: (2024)

Tracing the Path to Grokking: Embeddings, Dropout, and Network Activation
por: Salah, Ahmed, et al.
Publicado: (2025)

Tool-Aided Evolutionary LLM for Generative Policy Toward Efficient Resource Management in Wireless Federated Learning
por: Tan, Chongyang, et al.
Publicado: (2025)

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

Efficient Federated Learning with Heterogeneous Data and Adaptive Dropout
por: Liu, Ji, et al.
Publicado: (2025)

LCGuard: Latent Communication Guard for Safe KV Sharing in Multi-Agent Systems
por: Asif, Sadia, et al.
Publicado: (2026)

Dropout Robustness and Cognitive Profiling of Transformer Models via Stochastic Inference
por: Caiado, Antônio Junior Alves, et al.
Publicado: (2026)

IFFair: Influence Function-driven Sample Reweighting for Fair Classification
por: Yang, Jingran, et al.
Publicado: (2025)

Optimizing Deep Neural Networks using Safety-Guided Self Compression
por: Zbeeb, Mohammad, et al.
Publicado: (2025)

Lattice: Learning to Efficiently Compress the Memory
por: Karami, Mahdi, et al.
Publicado: (2025)

A Mathematical Framework for Temporal Modeling and Counterfactual Policy Simulation of Student Dropout
por: da Silva, Rafael, et al.
Publicado: (2026)

Reinforcement Learning in Switching Non-Stationary Markov Decision Processes: Algorithms and Convergence Analysis
por: Amiri, Mohsen, et al.
Publicado: (2025)

Fine-Grained Graph Generation through Latent Mixture Scheduling
por: Vakil, Nidhi, et al.
Publicado: (2026)

MU-Bench: A Multitask Multimodal Benchmark for Machine Unlearning
por: Cheng, Jiali, et al.
Publicado: (2024)

Curriculum Learning for LLM Pretraining: An Analysis of Learning Dynamics
por: Elgaar, Mohamed, et al.
Publicado: (2026)

Revisiting Data Attribution for Influence Functions
por: Zhu, Hongbo, et al.
Publicado: (2025)

Influence Functions for Preference Dataset Pruning
por: Fein, Daniel, et al.
Publicado: (2025)

Efficient Federated Fine-Tuning of Large Language Models with Layer Dropout
por: Wang, Shilong, et al.
Publicado: (2025)

DipSVD: Dual-importance Protected SVD for Efficient LLM Compression
por: Ding, Xuan, et al.
Publicado: (2025)