Imagen de Portada

Exploring Variance Reduction in Importance Sampling for Efficient DNN Training

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autor principal:	Kutsuna, Takuro
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Linearly Constrained Weights: Reducing Activation Shift for Faster Training of Neural Networks
por: Kutsuna, Takuro
Publicado: (2024)

A Probabilistic Formulation of Offset Noise in Diffusion Models
por: Kutsuna, Takuro
Publicado: (2024)

Residual Prior Diffusion: A Probabilistic Framework Integrating Coarse Latent Priors with Diffusion Models
por: Kutsuna, Takuro
Publicado: (2025)

Minimal Sufficient Views: A DNN model making predictions with more evidence has higher accuracy
por: Kawano, Keisuke, et al.
Publicado: (2024)

One-Shot Domain Incremental Learning
por: Esaki, Yasushi, et al.
Publicado: (2024)

An Asymptotic Equation Linking WAIC and WBIC in Singular Models
por: Hayashi, Naoki, et al.
Publicado: (2025)

Accuracy-Preserving Calibration via Statistical Modeling on Probability Simplex
por: Esaki, Yasushi, et al.
Publicado: (2024)

Generative climate downscaling enables high-resolution compound risk assessment by preserving multivariate dependencies
por: Kutsuna, Takuro, et al.
Publicado: (2026)

NMS: Efficient Edge DNN Training via Near-Memory Sampling on Manifolds
por: Zhao, Boran, et al.
Publicado: (2025)

Low Variance Off-policy Evaluation with State-based Importance Sampling
por: Bossens, David M., et al.
Publicado: (2022)

Rethinking the Potential of Layer Freezing for Efficient DNN Training
por: Yang, Chence, et al.
Publicado: (2025)

Efficient Backpropagation with Variance-Controlled Adaptive Sampling
por: Wang, Ziteng, et al.
Publicado: (2024)

Variance-Reduction Guidance: Sampling Trajectory Optimization for Diffusion Models
por: Xu, Shifeng, et al.
Publicado: (2025)

MARS: Unleashing the Power of Variance Reduction for Training Large Models
por: Yuan, Huizhuo, et al.
Publicado: (2024)

Zeroth-Order Non-Log-Concave Sampling with Variance Reduction and Applications to Inverse Problems
por: Sahin, M. Berk, et al.
Publicado: (2026)

AdapSNE: Adaptive Fireworks-Optimized and Entropy-Guided Dataset Sampling for Edge DNN Training
por: Zhao, Boran, et al.
Publicado: (2025)

PaSE: Parallelization Strategies for Efficient DNN Training
por: Elango, Venmugil
Publicado: (2024)

Variance Reduction in Ratio Metrics for Efficient Online Experiments
por: Baweja, Shubham, et al.
Publicado: (2024)

DNN Memory Footprint Reduction via Post-Training Intra-Layer Multi-Precision Quantization
por: Ghavami, Behnam, et al.
Publicado: (2024)

Conformal Risk Minimization with Variance Reduction
por: Noorani, Sima, et al.
Publicado: (2024)

DNN Modularization via Activation-Driven Training
por: Ngo, Tuan, et al.
Publicado: (2024)

VAMO: Efficient Zeroth-Order Variance Reduction for SGD with Faster Convergence
por: Chen, Jiahe, et al.
Publicado: (2025)

Efficient Sign-Based Optimization: Accelerating Convergence via Variance Reduction
por: Jiang, Wei, et al.
Publicado: (2024)

Variance Reduction and Low Sample Complexity in Stochastic Optimization via Proximal Point Method
por: Liang, Jiaming
Publicado: (2024)

SPRINT: Stochastic Performative Prediction With Variance Reduction
por: Xie, Tian, et al.
Publicado: (2025)

Variance Reduction via Resampling and Experience Replay
por: Han, Jiale, et al.
Publicado: (2025)

On the Reduction of Variance and Overestimation of Deep Q-Learning
por: Sabry, Mohammed, et al.
Publicado: (2019)

DAF: An Efficient End-to-End Dynamic Activation Framework for on-Device DNN Training
por: Liu, Renyuan, et al.
Publicado: (2025)

Efficient and Unbiased Sampling from Boltzmann Distributions via Variance-Tuned Diffusion Models
por: Zhang, Fengzhe, et al.
Publicado: (2025)

Variance Reduction for the Independent Metropolis Sampler
por: Liu, Siran, et al.
Publicado: (2024)

On Variance Reduction in Learning Mean Flows
por: Lu, Juanwu, et al.
Publicado: (2026)

Variance Reduction Based Experience Replay for Policy Optimization
por: Zheng, Hua, et al.
Publicado: (2026)

MAx-DNN: Multi-Level Arithmetic Approximation for Energy-Efficient DNN Hardware Accelerators
por: Leon, Vasileios, et al.
Publicado: (2025)

DecTrain: Deciding When to Train a Monocular Depth DNN Online
por: Fu, Zih-Sing, et al.
Publicado: (2024)

Learning to Importance Sample in Primary Sample Space
por: Zheng, Quan, et al.
Publicado: (2018)

Annealed Importance Sampling with q-Paths
por: Brekelmans, Rob, et al.
Publicado: (2020)

Actor-Critic with Active Importance Sampling
por: Molaei, Majid, et al.
Publicado: (2026)

Policy Gradient with Active Importance Sampling
por: Papini, Matteo, et al.
Publicado: (2024)

Optimal-Point Variance Reduction For Bayesian Optimization With Regret Guarantee
por: Takeno, Shion
Publicado: (2026)

Revisiting DNN Training for Intermittently-Powered Energy-Harvesting Micro-Computers
por: Mishra, Cyan Subhra, et al.
Publicado: (2024)