Copertina

Loss Gradient Gaussian Width based Generalization and Optimization Guarantees

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Banerjee, Arindam, Li, Qiaobo, Zhou, Yingxue
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Sketched Gaussian Mechanism for Private Federated Learning
di: Li, Qiaobo, et al.
Pubblicazione: (2025)

Sketched Adaptive Federated Deep Learning: A Sharp Convergence Analysis
di: Chen, Zhijie, et al.
Pubblicazione: (2024)

Beyond Johnson-Lindenstrauss: Uniform Bounds for Sketched Bilinear Forms
di: Deb, Rohan, et al.
Pubblicazione: (2025)

Optimization for Neural Operators can Benefit from Width
di: Cisneros-Velarde, Pedro, et al.
Pubblicazione: (2025)

Optimization and Generalization Guarantees for Weight Normalization
di: Cisneros-Velarde, Pedro, et al.
Pubblicazione: (2024)

Inference Time Policy Optimization for Offline RL with Differentiable World Models
di: Deb, Rohan, et al.
Pubblicazione: (2026)

Gradual Fine-Tuning for Flow Matching Models
di: Thorkelsdottir, Gudrun, et al.
Pubblicazione: (2026)

Efficient Techniques for Data Reconstruction, with Finite-Width Recovery Guarantees
di: Tansley, Edward, et al.
Pubblicazione: (2026)

Plan Before You Trade: Inference-Time Optimization for RL Trading Agents
di: Go, Eun, et al.
Pubblicazione: (2026)

Generalization Guarantees of Gradient Descent for Multi-Layer Neural Networks
di: Wang, Puyu, et al.
Pubblicazione: (2023)

Replicable Bandits with UCB based Exploration
di: Deb, Rohan, et al.
Pubblicazione: (2026)

Optimization Guarantees for Square-Root Natural-Gradient Variational Inference
di: Kumar, Navish, et al.
Pubblicazione: (2025)

Optimal Guarantees for Algorithmic Reproducibility and Gradient Complexity in Convex Optimization
di: Zhang, Liang, et al.
Pubblicazione: (2023)

Bridging SFT and RL: Dynamic Policy Optimization for Robust Reasoning
di: Zhu, Taojie, et al.
Pubblicazione: (2026)

Generalization Guarantees on Data-Driven Tuning of Gradient Descent with Langevin Updates
di: Goyal, Saumya, et al.
Pubblicazione: (2026)

Gaussian Process Inference Using Mini-batch Stochastic Gradient Descent: Convergence Guarantees and Empirical Benefits
di: Chen, Hao, et al.
Pubblicazione: (2021)

Statistical Guarantees for High-Dimensional Stochastic Gradient Descent
di: Li, Jiaqi, et al.
Pubblicazione: (2025)

Local Loss Optimization in the Infinite Width: Stable Parameterization of Predictive Coding Networks and Target Propagation
di: Ishikawa, Satoki, et al.
Pubblicazione: (2024)

Differentially Private Post-Processing for Fair Regression
di: Xian, Ruicheng, et al.
Pubblicazione: (2024)

Conservative Contextual Bandits: Beyond Linear Representations
di: Deb, Rohan, et al.
Pubblicazione: (2024)

Large Stepsize Gradient Descent for Logistic Loss: Non-Monotonicity of the Loss Improves Optimization Efficiency
di: Wu, Jingfeng, et al.
Pubblicazione: (2024)

Gradient Flow Convergence Guarantee for General Neural Network Architectures
di: Jakhmola, Yash
Pubblicazione: (2025)

Clustering-based Meta Bayesian Optimization with Theoretical Guarantee
di: Nguyen, Khoa, et al.
Pubblicazione: (2025)

Neural Exploitation and Exploration of Contextual Bandits
di: Ban, Yikun, et al.
Pubblicazione: (2023)

On the Optimization and Generalization of Two-layer Transformers with Sign Gradient Descent
di: Li, Bingrui, et al.
Pubblicazione: (2024)

An energy-efficient spiking neural network with continuous learning for self-adaptive brain-machine interface
di: Biyan, Zhou, et al.
Pubblicazione: (2025)

Privacy of SGD under Gaussian or Heavy-Tailed Noise: Guarantees without Gradient Clipping
di: Şimşekli, Umut, et al.
Pubblicazione: (2024)

Minimum Width of Deep Narrow Networks for Universal Approximation
di: Yang, Xiao-Song, et al.
Pubblicazione: (2025)

Policy Gradient in Robust MDPs with Global Convergence Guarantee
di: Wang, Qiuhao, et al.
Pubblicazione: (2022)

Bayesian Risk-Sensitive Policy Optimization For MDPs With General Loss Functions
di: Wang, Xiaoshuang, et al.
Pubblicazione: (2025)

Geospatial Machine Learning Libraries
di: Stewart, Adam J., et al.
Pubblicazione: (2025)

Pyramid MoA: A Probabilistic Framework for Cost-Optimized Anytime Inference
di: Khaled, Arindam
Pubblicazione: (2026)

Lai Loss: A Novel Loss for Gradient Control
di: Lai, YuFei
Pubblicazione: (2024)

On the Parameterization of Second-Order Optimization Effective Towards the Infinite Width
di: Ishikawa, Satoki, et al.
Pubblicazione: (2023)

AYLA: Amplifying Gradient Sensitivity via Loss Transformation in Non-Convex Optimization
di: Keslaki, Ben
Pubblicazione: (2025)

Conformal Risk Control under Non-Monotone Losses: Theory and Finite-Sample Guarantees
di: Aldirawi, Tareq, et al.
Pubblicazione: (2026)

A new graph-based surrogate model for rapid prediction of crashworthiness performance of vehicle panel components
di: Li, Haoran, et al.
Pubblicazione: (2025)

Multiclass Loss Geometry Matters for Generalization of Gradient Descent in Separable Classification
di: Schliserman, Matan, et al.
Pubblicazione: (2025)

Gearing Gaussian process modeling and sequential design towards stochastic simulators
di: Binois, Mickael, et al.
Pubblicazione: (2024)

Guaranteed Coverage Prediction Intervals with Gaussian Process Regression
di: Papadopoulos, Harris
Pubblicazione: (2023)