Copertina

Almost Free: Self-concordance in Natural Exponential Families and an Application to Bandits

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Liu, Shuai, Ayoub, Alex, Sentenac, Flore, Tan, Xiaoqi, Szepesvári, Csaba
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

Balancing optimism and pessimism in offline-to-online learning
di: Sentenac, Flore, et al.
Pubblicazione: (2025)

Learning What to Recommend: Minimax Optimal Simple Regret in Logistic Bandits
di: Liu, Shuai, et al.
Pubblicazione: (2026)

Exploration via linearly perturbed loss minimisation
di: Janz, David, et al.
Pubblicazione: (2023)

Rectifying Regression in Reinforcement Learning
di: Ayoub, Alex, et al.
Pubblicazione: (2025)

Sharper Guarantees for Misspecified Kernelized Bandit Optimization
di: Maran, Davide, et al.
Pubblicazione: (2026)

Learning to Reason Efficiently with Discounted Reinforcement Learning
di: Ayoub, Alex, et al.
Pubblicazione: (2025)

Eluder dimension: localise it!
di: Bakhtiari, Alireza, et al.
Pubblicazione: (2026)

Stochastic Gradient Succeeds for Bandits
di: Mei, Jincheng, et al.
Pubblicazione: (2024)

Confident Natural Policy Gradient for Local Planning in $q_π$-realizable Constrained MDPs
di: Tian, Tian, et al.
Pubblicazione: (2024)

Trajectory Data Suffices for Statistically Efficient Learning in Offline RL with Linear $q^π$-Realizability and Concentrability
di: Tkachuk, Volodymyr, et al.
Pubblicazione: (2024)

Sharp analysis of linear ensemble sampling
di: Akhavan, Arya, et al.
Pubblicazione: (2026)

Switching the Loss Reduces the Cost in Batch (Offline) Reinforcement Learning
di: Ayoub, Alex, et al.
Pubblicazione: (2024)

Ensemble sampling for linear bandits: small ensembles suffice
di: Janz, David, et al.
Pubblicazione: (2023)

The Challenger: When Do New Data Sources Justify Switching Machine Learning Models?
di: Digalakis Jr, Vassilis, et al.
Pubblicazione: (2025)

Beyond Statistical Learning: Exact Learning Is Essential for General Intelligence
di: György, András, et al.
Pubblicazione: (2025)

Optimistic Actor-Critic with Parametric Policies for Linear Markov Decision Processes
di: Lin, Max Qiushi, et al.
Pubblicazione: (2026)

Optimistic Policy Optimization is Provably Efficient in Non-stationary MDPs
di: Zhong, Han, et al.
Pubblicazione: (2021)

LACONIC: Length-Aware Constrained Reinforcement Learning for LLM
di: Liu, Chang, et al.
Pubblicazione: (2026)

Regret Minimization via Saddle Point Optimization
di: Kirschner, Johannes, et al.
Pubblicazione: (2024)

To Believe or Not to Believe Your LLM
di: Yadkori, Yasin Abbasi, et al.
Pubblicazione: (2024)

Guiding Time-Varying Generative Models with Natural Gradients on Exponential Family Manifold
di: Liu, Song, et al.
Pubblicazione: (2025)

Ordering-based Conditions for Global Convergence of Policy Gradient Methods
di: Mei, Jincheng, et al.
Pubblicazione: (2025)

Exponential Family Attention
di: Wibisono, Kevin Christian, et al.
Pubblicazione: (2025)

Almost Minimax Optimal Best Arm Identification in Piecewise Stationary Linear Bandits
di: Hou, Yunlong, et al.
Pubblicazione: (2024)

Small steps no more: Global convergence of stochastic gradient bandits for arbitrary learning rates
di: Mei, Jincheng, et al.
Pubblicazione: (2025)

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

Generalized Linear Bandits: Almost Optimal Regret with One-Pass Update
di: Zhang, Yu-Jie, et al.
Pubblicazione: (2025)

Frontier LLMs Still Struggle with Simple Reasoning Tasks
di: Malek, Alan, et al.
Pubblicazione: (2025)

Model Predictive Control is Almost Optimal for Restless Bandit
di: Gast, Nicolas, et al.
Pubblicazione: (2024)

Diffusion Models for Inverse Problems in the Exponential Family
di: Micheli, Alessandro, et al.
Pubblicazione: (2025)

Combinatorial Multivariant Multi-Armed Bandits with Applications to Episodic Reinforcement Learning and Beyond
di: Liu, Xutong, et al.
Pubblicazione: (2024)

Stein's Lemma for the Reparameterization Trick with Exponential Family Mixtures
di: Lin, Wu, et al.
Pubblicazione: (2019)

Tighter Regret Lower Bound for Gaussian Process Bandits with Squared Exponential Kernel in Hypersphere
di: Iwazaki, Shogo
Pubblicazione: (2026)

Stochastic Gradient Descent for Gaussian Processes Done Right
di: Lin, Jihao Andreas, et al.
Pubblicazione: (2023)

Rethinking the Global Convergence of Softmax Policy Gradient with Linear Function Approximation
di: Lin, Max Qiushi, et al.
Pubblicazione: (2025)

Optimal Analysis for Bandit Learning in Matching Markets with Serial Dictatorship
di: Wang, Zilong, et al.
Pubblicazione: (2025)

Scalable Frank-Wolfe on Generalized Self-concordant Functions via Simple Steps
di: Carderera, Alejandro, et al.
Pubblicazione: (2021)

Cascading Bandits Robust to Adversarial Corruptions
di: Xie, Jize, et al.
Pubblicazione: (2025)

Decentralized Asynchronous Multi-player Bandits
di: Fan, Jingqi, et al.
Pubblicazione: (2025)

On the Benefits of Free Exploration for Regret Minimization in Multi-Armed Bandits
di: Hou, Yunlong, et al.
Pubblicazione: (2026)