Imagen de Portada

From Entropy to Epiplexity: Rethinking Information for Computationally Bounded Intelligence

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Finzi, Marc, Qiu, Shikai, Jiang, Yiding, Izmailov, Pavel, Kolter, J. Zico, Wilson, Andrew Gordon
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Large Language Models Are Zero-Shot Time Series Forecasters
por: Gruver, Nate, et al.
Publicado: (2023)

Compute Better Spent: Replacing Dense Layers with Structured Matrices
por: Qiu, Shikai, et al.
Publicado: (2024)

Predicting the Performance of Black-box LLMs through Follow-up Queries
por: Sam, Dylan, et al.
Publicado: (2025)

Diffusing Differentiable Representations
por: Savani, Yash, et al.
Publicado: (2024)

Compute-Optimal LLMs Provably Generalize Better With Scale
por: Finzi, Marc, et al.
Publicado: (2025)

Forgetting in Language Models: Capacity, Optimization, and Self-Generated Replay
por: Marek, Martin, et al.
Publicado: (2026)

Looking beyond the next token
por: Thankaraj, Abitha, et al.
Publicado: (2025)

Adaptive Data Optimization: Dynamic Sample Selection with Scaling Laws
por: Jiang, Yiding, et al.
Publicado: (2024)

Unlocking Tokens as Data Points for Generalization Bounds on Larger Language Models
por: Lotfi, Sanae, et al.
Publicado: (2024)

The No Free Lunch Theorem, Kolmogorov Complexity, and the Role of Inductive Biases in Machine Learning
por: Goldblum, Micah, et al.
Publicado: (2023)

Non-Vacuous Generalization Bounds for Large Language Models
por: Lotfi, Sanae, et al.
Publicado: (2023)

Rethinking Distance Metrics for Counterfactual Explainability
por: Williams, Joshua Nathaniel, et al.
Publicado: (2024)

Searching for Efficient Linear Layers over a Continuous Space of Structured Matrices
por: Potapczynski, Andres, et al.
Publicado: (2024)

Scaling Collapse Reveals Universal Dynamics in Compute-Optimally Trained Neural Networks
por: Qiu, Shikai, et al.
Publicado: (2025)

The Lie Derivative for Measuring Learned Equivariance
por: Gruver, Nate, et al.
Publicado: (2022)

AcceleratedLiNGAM: Learning Causal DAGs at the speed of GPUs
por: Akinwande, Victor, et al.
Publicado: (2024)

FUSE-ing Language Models: Zero-Shot Adapter Discovery for Prompt Optimization Across Tokenizers
por: Williams, Joshua Nathaniel, et al.
Publicado: (2024)

Equilibrium Reasoners: Learning Attractors Enables Scalable Reasoning
por: Huang, Benhao, et al.
Publicado: (2026)

Why is SAM Robust to Label Noise?
por: Baek, Christina, et al.
Publicado: (2024)

Rethinking LLM Memorization through the Lens of Adversarial Compression
por: Schwarzschild, Avi, et al.
Publicado: (2024)

Mimetic Initialization of MLPs
por: Trockman, Asher, et al.
Publicado: (2026)

Provably Bounding Neural Network Preimages
por: Kotha, Suhas, et al.
Publicado: (2023)

Hyperparameter Transfer Enables Consistent Gains of Matrix-Preconditioned Optimizers Across Scales
por: Qiu, Shikai, et al.
Publicado: (2025)

Evaluating Language Model Reasoning about Confidential Information
por: Sam, Dylan, et al.
Publicado: (2025)

Scaling Laws for Data Filtering -- Data Curation cannot be Compute Agnostic
por: Goyal, Sachin, et al.
Publicado: (2024)

Training a Generally Curious Agent
por: Tajwar, Fahim, et al.
Publicado: (2025)

One-Step Diffusion Distillation via Deep Equilibrium Models
por: Geng, Zhengyang, et al.
Publicado: (2023)

Measuring Five-Nines Reliability: Sample-Efficient LLM Evaluation in Saturated Benchmarks
por: Kim, Eungyeup, et al.
Publicado: (2026)

Generative Posterior Networks for Approximately Bayesian Epistemic Uncertainty Estimation
por: Roderick, Melrose, et al.
Publicado: (2023)

Neural Network Verification with Branch-and-Bound for General Nonlinearities
por: Shi, Zhouxing, et al.
Publicado: (2024)

Customizing the Inductive Biases of Softmax Attention using Structured Matrices
por: Kuang, Yilun, et al.
Publicado: (2025)

Can a Confident Prior Replace a Cold Posterior?
por: Marek, Martin, et al.
Publicado: (2024)

An Axiomatic Approach to Model-Agnostic Concept Explanations
por: Feng, Zhili, et al.
Publicado: (2024)

The Mixing method: low-rank coordinate descent for semidefinite programming with diagonal constraints
por: Wang, Po-Wei, et al.
Publicado: (2017)

Context-Parametric Inversion: Why Instruction Finetuning Can Worsen Context Reliance
por: Goyal, Sachin, et al.
Publicado: (2024)

Massive Activations in Large Language Models
por: Sun, Mingjie, et al.
Publicado: (2024)

From Variance to Veracity: Unbundling and Mitigating Gradient Variance in Differentiable Bundle Adjustment Layers
por: Gurumurthy, Swaminathan, et al.
Publicado: (2024)

Transferring Knowledge from Large Foundation Models to Small Downstream Models
por: Qiu, Shikai, et al.
Publicado: (2024)

ROGUE: Misaligned Agent Behavior Arising from Ordinary Computer Use
por: Tien, Jeremy, et al.
Publicado: (2026)

Safety Pretraining: Toward the Next Generation of Safe AI
por: Maini, Pratyush, et al.
Publicado: (2025)