paper-with-me

Papers

The Conditional Regret-Capacity Theorem for Batch Universal Prediction

2025-08-14 · Marco Bondaschi, Michael Gastpar arxiv

We derive a conditional version of the classical regret-capacity theorem. This result can be used in universal prediction to find lower bounds on the minimal batch regret, which is a recently introduced generalization of the average regret, when batches of training data are available to the predictor. As an example, we apply this result to the class of binary memoryless sources. Finally, we generalize the theorem to Rényi information measures, revealing a deep connection between the conditional Rényi divergence and the conditional Sibson's mutual information.

📄 PDF Abstract BibTeX arXiv:2508.10282

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Universal Batch Learning Under The Misspecification Setting

2024-05-12 · Shlomi Vituri, Meir Feder

In this paper we consider the problem of universal {\em batch} learning in a misspecification setting with log-loss. In this setting the hypothesis class is a set of models $\Theta$. However, the data is generated by an …

Almost Optimal Batch-Regret Tradeoff for Batch Linear Contextual Bandits

2021-10-15 · Zihan Zhang, Xiangyang Ji, Yuan Zhou

We study the optimal batch-regret tradeoff for batch linear contextual bandits. For any batch number $M$, number of actions $K$, time horizon $T$, and dimension $d$, we provide an algorithm and prove its regret guarantee…

Multi-Armed Bandits

Batch Universal Prediction

2024-02-06 · Marco Bondaschi, Michael Gastpar

Large language models (LLMs) have recently gained much popularity due to their surprising ability at generating human-like English sentences. LLMs are essentially predictors, estimating the probability of a sequence of w…

Prediction

Universal approximation theorem for neural networks with inputs from a topological vector space

2024-09-19 · Vugar Ismailov

We study feedforward neural networks with inputs from a topological vector space (TVS-FNNs). Unlike traditional feedforward neural networks, TVS-FNNs can process a broader range of inputs, including sequences, matrices, …

Online Linear Programming with Batching

2024-08-01 · Haoran Xu, Peter W. Glynn, Yinyu Ye

We study Online Linear Programming (OLP) with batching. The planning horizon is cut into $K$ batches, and the decisions on customers arriving within a batch can be delayed to the end of their associated batch. Compared w…