Imagen de Portada

AYLA: Amplifying Gradient Sensitivity via Loss Transformation in Non-Convex Optimization

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autor principal:	Keslaki, Ben
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

DRIFT: Data Reduction via Informative Feature Transformation- Generalization Begins Before Deep Learning starts
por: Keslaki, Ben
Publicado: (2025)

Stochastic Non-Smooth Convex Optimization with Unbounded Gradients
por: Kovalev, Dmitry
Publicado: (2026)

Quantitative Convergence Analysis of Projected Stochastic Gradient Descent for Non-Convex Losses via the Goldstein Subdifferential
por: Zheng, Yuping, et al.
Publicado: (2025)

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

Mitigating Gradient Overlap in Deep Residual Networks with Gradient Normalization for Improved Non-Convex Optimization
por: Yun, Juyoung
Publicado: (2024)

Simple Optimizers for Convex Aligned Multi-Objective Optimization
por: Kretzu, Ben, et al.
Publicado: (2025)

The Dimension Strikes Back with Gradients: Generalization of Gradient Methods in Stochastic Convex Optimization
por: Schliserman, Matan, et al.
Publicado: (2024)

More Optimal Fractional-Order Stochastic Gradient Descent for Non-Convex Optimization Problems
por: Partohaghighi, Mohammad, et al.
Publicado: (2025)

Bandit Convex Optimization with Gradient Prediction Adaptivity
por: Wang, Shuche, et al.
Publicado: (2026)

Shuffling Momentum Gradient Algorithm for Convex Optimization
por: Tran, Trang H., et al.
Publicado: (2024)

Improved Dimension Dependence for Bandit Convex Optimization with Gradient Variations
por: Yu, Hang, et al.
Publicado: (2026)

On Convergence of Incremental Gradient for Non-Convex Smooth Functions
por: Koloskova, Anastasia, et al.
Publicado: (2023)

Non-Convex Optimization with Spectral Radius Regularization
por: Sandler, Adam, et al.
Publicado: (2021)

It's Our Loss: No Privacy Amplification for Hidden State DP-SGD With Non-Convex Loss
por: Annamalai, Meenatchi Sundaram Muthu Selva
Publicado: (2024)

On Convex Optimization with Semi-Sensitive Features
por: Ghazi, Badih, et al.
Publicado: (2024)

Non-Convex Optimization in Federated Learning via Variance Reduction and Adaptive Learning
por: Thakur, Dipanwita, et al.
Publicado: (2024)

The Sample Complexity of Gradient Descent in Stochastic Convex Optimization
por: Livni, Roi
Publicado: (2024)

Small Gradient Norm Regret for Online Convex Optimization
por: Gao, Wenzhi, et al.
Publicado: (2026)

Adaptive Proximal Gradient Method for Convex Optimization
por: Malitsky, Yura, et al.
Publicado: (2023)

Grokfast: Accelerated Grokking by Amplifying Slow Gradients
por: Lee, Jaerin, et al.
Publicado: (2024)

Expressive Losses for Verified Robustness via Convex Combinations
por: De Palma, Alessandro, et al.
Publicado: (2023)

Convex Distillation: Efficient Compression of Deep Networks via Convex Optimization
por: Varshney, Prateek, et al.
Publicado: (2024)

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

An Accelerated Gradient Method for Convex Smooth Simple Bilevel Optimization
por: Cao, Jincheng, et al.
Publicado: (2024)

How to Make the Gradients Small Privately: Improved Rates for Differentially Private Non-Convex Optimization
por: Lowy, Andrew, et al.
Publicado: (2024)

Establishing Linear Surrogate Regret Bounds for Convex Smooth Losses via Convolutional Fenchel-Young Losses
por: Cao, Yuzhou, et al.
Publicado: (2025)

Convergence Error Analysis of Reflected Gradient Langevin Dynamics for Globally Optimizing Non-Convex Constrained Problems
por: Sato, Kanji, et al.
Publicado: (2022)

Loss Gradient Gaussian Width based Generalization and Optimization Guarantees
por: Banerjee, Arindam, et al.
Publicado: (2024)

Federated Smoothing Proximal Gradient for Quantile Regression with Non-Convex Penalties
por: Mirzaeifard, Reza, et al.
Publicado: (2024)

Projection-Free Online Convex Optimization with Time-Varying Constraints
por: Garber, Dan, et al.
Publicado: (2024)

Non-stationary Bandit Convex Optimization: A Comprehensive Study
por: Liu, Xiaoqi, et al.
Publicado: (2025)

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

Nesterov Finds GRAAL: Optimal and Adaptive Gradient Method for Convex Optimization
por: Borodich, Ekaterina, et al.
Publicado: (2025)

You Shall Pass: Dealing with the Zero-Gradient Problem in Predict and Optimize for Convex Optimization
por: Veviurko, Grigorii, et al.
Publicado: (2023)

Efficient Test-Time Finetuning of LLMs via Convex Reconstruction and Gradient Caching
por: Khamis, Alaa, et al.
Publicado: (2026)

Online Non-Stationary Stochastic Quasar-Convex Optimization
por: Pun, Yuen-Man, et al.
Publicado: (2024)

Muon in Vision Transformers: Optimizer-Recipe Interactions and Gradient Spectra
por: Southworth, Ben S., et al.
Publicado: (2026)

Understanding Transformer Optimization via Gradient Heterogeneity
por: Tomihari, Akiyoshi, et al.
Publicado: (2025)

Bayesian Optimization for Non-Convex Two-Stage Stochastic Optimization Problems
por: Buckingham, Jack M., et al.
Publicado: (2024)

Stochastic Momentum Methods for Non-smooth Non-Convex Finite-Sum Coupled Compositional Optimization
por: Chen, Xingyu, et al.
Publicado: (2025)