Imagen de Portada

Online Structured Prediction with Fenchel--Young Losses and Improved Surrogate Regret for Online Multiclass Classification with Logistic Loss

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Sakaue, Shinsaku, Bao, Han, Tsuchiya, Taira, Oki, Taihei
Formato:	Preprint
Publicado:	2024
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Revisiting Online Learning Approach to Inverse Linear Optimization: A Fenchel$-$Young Loss Perspective and Gap-Dependent Regret Analysis
por: Sakaue, Shinsaku, et al.
Publicado: (2025)

Online Inverse Linear Optimization: Efficient Logarithmic-Regret Algorithm, Robustness to Suboptimality, and Lower Bound
por: Sakaue, Shinsaku, et al.
Publicado: (2025)

Finite and Corruption-Robust Regret Bounds in Online Inverse Linear Optimization under M-Convex Action Sets
por: Oki, Taihei, et al.
Publicado: (2026)

Non-Stationary Online Structured Prediction with Surrogate Losses
por: Sakaue, Shinsaku, et al.
Publicado: (2025)

No-Regret M${}^{\natural}$-Concave Function Maximization: Stochastic Bandit Algorithms and Hardness of Adversarial Full-Information Setting
por: Oki, Taihei, et al.
Publicado: (2024)

Any-stepsize Gradient Descent for Separable Data under Fenchel-Young Losses
por: Bao, Han, et al.
Publicado: (2025)

Generalization Bound and Learning Methods for Data-Driven Projections in Linear Programming
por: Sakaue, Shinsaku, et al.
Publicado: (2023)

Bandit and Delayed Feedback in Online Structured Prediction
por: Shibukawa, Yuki, et al.
Publicado: (2025)

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

From Average Sensitivity to Small-Loss Regret Bounds under Random-Order Model
por: Sakaue, Shinsaku, et al.
Publicado: (2026)

Simple Projection-Free Algorithm for Contextual Recommendation with Logarithmic Regret and Robustness
por: Sakaue, Shinsaku
Publicado: (2026)

Data- and Variance-dependent Regret Bounds for Online Tabular MDPs
por: Li, Mingyi, et al.
Publicado: (2026)

A Simple and Adaptive Learning Rate for FTRL in Online Learning with Minimax Regret of $Θ(T^{2/3})$ and its Application to Best-of-Both-Worlds
por: Tsuchiya, Taira, et al.
Publicado: (2024)

Non-stationary Online Learning for Curved Losses: Improved Dynamic Regret via Mixability
por: Zhang, Yu-Jie, et al.
Publicado: (2025)

Fast Rates in Stochastic Online Convex Optimization by Exploiting the Curvature of Feasible Sets
por: Tsuchiya, Taira, et al.
Publicado: (2024)

Tight Regret Upper and Lower Bounds for Optimistic Hedge in Two-Player Zero-Sum Games
por: Tsuchiya, Taira
Publicado: (2025)

A Fenchel-Young Loss Approach to Data-Driven Inverse Optimization
por: Li, Zhehao, et al.
Publicado: (2025)

Online Control of Linear Systems under Unbounded Noise
por: Ito, Kaito, et al.
Publicado: (2024)

Learning Differentiable Surrogate Losses for Structured Prediction
por: Yang, Junjie, et al.
Publicado: (2024)

Beyond Bandit Feedback in Online Multiclass Classification
por: van der Hoeven, Dirk, et al.
Publicado: (2021)

Linear-Core Surrogates: Smooth Loss Functions with Linear Rates for Classification and Structured Prediction
por: Mohri, Mehryar, et al.
Publicado: (2026)

Bandit-Feedback Online Multiclass Classification: Variants and Tradeoffs
por: Filmus, Yuval, et al.
Publicado: (2024)

Classification with Deep Neural Networks and Logistic Loss
por: Zhang, Zihan, et al.
Publicado: (2023)

Exploration by Optimization with Hybrid Regularizers: Logarithmic Regret with Adversarial Robustness in Partial Monitoring
por: Tsuchiya, Taira, et al.
Publicado: (2024)

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

Learning from Samples: Inverse Problems over measures via Sharpened Fenchel-Young Losses
por: Andrade, Francisco, et al.
Publicado: (2025)

Online AUC Optimization Based on Second-order Surrogate Loss
por: Luo, JunRu, et al.
Publicado: (2025)

Adapting to Stochastic and Adversarial Losses in Episodic MDPs with Aggregate Bandit Feedback
por: Ito, Shinji, et al.
Publicado: (2025)

Multiclass Transductive Online Learning
por: Hanneke, Steve, et al.
Publicado: (2024)

Lower Bounds on Adversarial Robustness for Multiclass Classification with General Loss Functions
por: Trillos, Camilo Andrés García, et al.
Publicado: (2025)

Fenchel-Young Variational Learning
por: Sklaviadis, Sophia, et al.
Publicado: (2025)

Improved Dynamic Regret for Online Frank-Wolfe
por: Wan, Yuanyu, et al.
Publicado: (2023)

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

Universal Multiclass Transductive Online Learning
por: Hanneke, Steve, et al.
Publicado: (2026)

Online Learning with Improving Agents: Multiclass, Budgeted Agents and Bandit Learners
por: Ashkezari, Sajad, et al.
Publicado: (2026)

Online Algorithm for Aggregating Experts' Predictions with Unbounded Quadratic Loss
por: Korotin, Alexander, et al.
Publicado: (2025)

The Multiclass Score-Oriented Loss (MultiSOL) on the Simplex
por: Marchetti, Francesco, et al.
Publicado: (2025)

Detecting Hope Across Languages: Multiclass Classification for Positive Online Discourse
por: Abiola, T. O., et al.
Publicado: (2025)

Multiclass Online Learnability under Bandit Feedback
por: Raman, Ananth, et al.
Publicado: (2023)

Improved Online Confidence Bounds for Multinomial Logistic Bandits
por: Lee, Joongkyu, et al.
Publicado: (2025)