Cover Image

An Information-Theoretic Perspective on LLM Tokenizers

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Erdogan, Mete, Gorle, Abhiram, Chandak, Shubham, Pilanci, Mert, Weissman, Tsachy
Format:	Preprint
Published:	2026
Subjects:	Information Theory
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

ItDPDM: Information-Theoretic Discrete Poisson Diffusion Model
by: Bhattacharya, Sagnik, et al.
Published: (2025)

Information-computation trade-offs in non-linear transforms
by: Ding, Connor, et al.
Published: (2025)

LZMidi: Compression-Based Symbolic Music Generation
by: Ding, Connor, et al.
Published: (2025)

An Information-Theoretic Efficient Capacity Region for Multi-User Interference Channel
by: Bhattacharya, Sagnik, et al.
Published: (2025)

The Performance of Compression-Based Denoisers
by: Song, Dan, et al.
Published: (2025)

Optimal No-regret Learning in Repeated First-price Auctions
by: Han, Yanjun, et al.
Published: (2020)

The LZ78 Source
by: Sagan, Naomi, et al.
Published: (2025)

minPIC: Towards Optimal Power Allocation in Multi-User Interference Channels
by: Bhattacharya, Sagnik, et al.
Published: (2025)

A Family of LZ78-based Universal Sequential Probability Assignments
by: Sagan, Naomi, et al.
Published: (2024)

Universal Discrete Filtering with Lookahead or Delay
by: Yan, Pumiao, et al.
Published: (2025)

Optimal Scalar Quantization for Matrix Multiplication: Closed-Form Density and Phase Transition
by: Ang, Calvin, et al.
Published: (2026)

Learning to Bid Optimally and Efficiently in Adversarial First-price Auctions
by: Han, Yanjun, et al.
Published: (2020)

Newton Meets Marchenko-Pastur: Massively Parallel Second-Order Optimization with Hessian Sketching and Debiasing
by: Romanov, Elad, et al.
Published: (2024)

Stability and Synchronization of Kuramoto Oscillators
by: Gorle, Abhiram
Published: (2024)

Information Theoretic Perspective on Representation Learning
by: Pereg, Deborah, et al.
Published: (2026)

An Information Theoretic Perspective on Conformal Prediction
by: Correia, Alvaro H. C., et al.
Published: (2024)

A Generalized Information Bottleneck Method: A Decision-Theoretic Perspective
by: Kamatsuka, Akira, et al.
Published: (2026)

Secure Event-triggered MolecularvCommunication - Information Theoretic Perspective and Optimal Performance
by: Labidi, Wafa, et al.
Published: (2025)

An Information-Theoretic Perspective on Variance-Invariance-Covariance Regularization
by: Shwartz-Ziv, Ravid, et al.
Published: (2023)

Analyzing Multimodal Integration in the Variational Autoencoder from an Information-Theoretic Perspective
by: Langer, Carlotta, et al.
Published: (2024)

On the Hardness of Unsupervised Domain Adaptation: Optimal Learners and Information-Theoretic Perspective
by: Dong, Zhiyi, et al.
Published: (2025)

Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective
by: Laakom, Firas, et al.
Published: (2025)

Energy Efficiency Analysis of IRS-aided Wireless Communication Systems Under Statistical QoS Constraints: An Information-Theoretic Perspective
by: Wang, Wenhao, et al.
Published: (2024)

Uncertainty Quantification and Data Efficiency in AI: An Information-Theoretic Perspective
by: Simeone, Osvaldo, et al.
Published: (2025)

An Information Theoretic Perspective on Agentic System Design
by: He, Shizhe, et al.
Published: (2025)

Pufferfish Privacy: An Information-Theoretic Study
by: Nuradha, Theshani, et al.
Published: (2022)

Gradient Coding with Iterative Block Leverage Score Sampling
by: Charalambides, Neophytos, et al.
Published: (2023)

Information-Theoretic Secure Aggregation in Decentralized Networks
by: Zhang, Xiang, et al.
Published: (2026)

Information-Theoretic Privacy with General Distortion Constraints
by: Kalantari, Kousha, et al.
Published: (2017)

A Game-Theoretic Perspective for Efficient Modern Random Access
by: Hansen, Andreas Peter Juhl, et al.
Published: (2024)

Covert Communication over Physically-Degraded Alarm Two-Way Channels
by: Erdoğan, Tuna, et al.
Published: (2025)

Information-Theoretic Limits on Exact Subgraph Alignment Problem
by: Shiu, Chun Hei Michael, et al.
Published: (2026)

Information-Theoretic Secure Aggregation over Regular Graphs
by: Zhang, Xiang, et al.
Published: (2026)

Information-Theoretic Decentralized Secure Aggregation with User Dropouts
by: Li, Zhou, et al.
Published: (2026)

Information-Theoretic Limits of Bistatic Integrated Sensing and Communication
by: Jiao, Tian, et al.
Published: (2023)

A Toolbox for Refined Information-Theoretic Analyses with Applications
by: Merhav, Neri, et al.
Published: (2024)

Two-Level Priority Coding for Resilience to Arbitrary Blockage Patterns
by: Dogan, Mine Gokce, et al.
Published: (2025)

Exploiting the Degrees of Freedom: Multi-Dimensional Spatially-Coupled Codes Based on Gradient Descent
by: Tanrıkulu, Ata, et al.
Published: (2026)

A Markov Chain Monte Carlo Method for Efficient Finite-Length LDPC Code Design
by: Tanrıkulu, Ata, et al.
Published: (2025)

Simple Finite-Length Achievability and Converse Bounds for the Deletion Channel and the Insertion Channel
by: Morozov, Ruslan, et al.
Published: (2025)